Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the beginning of new paragraphs or sections in text.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    phrases and words that indicate a commitment to service and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Start of a new turn or section

    np_acts-logits-general · gemini-2.0-flash

    structural tokens after segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]")]
    -0.69
    createCanvas
    -0.61
    MLLoader
    -0.61
     <>",
    -0.60
    évaluateur
    -0.58
     témoig
    -0.56
     diſt
    -0.54
    лтамалар
    -0.54
     ſind
    -0.53
    SOLVED
    -0.53
    POSITIVE LOGITS
     concepts
    0.35
     Pre
    0.34
    ebilir
    0.34
     пом
    0.33
    rinology
    0.33
    ide
    0.33
     inspiration
    0.32
    Pare
    0.32
     Hatch
    0.31
     permitan
    0.31
    Act Density 0.350%

    No Known Activations