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

    Neuronpedia

    INDEX
    Explanations

    dialogue and expressions of personal feelings or intentions

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

    Dialogue or reported speech

    np_acts-logits-general · gemini-2.0-flash

    But following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     >=",
    -0.73
    ✨:
    -0.69
    ⓧ
    -0.69
     lenker
    -0.68
    OOTDTY
    -0.63
    Welp
    -0.62
    batore
    -0.61
    σκ
    -0.58
     downright
    -0.58
     <>",
    -0.57
    POSITIVE LOGITS
     very
    0.61
    vikle
    0.58
     vanske
    0.56
     everywhere
    0.55
     informaciones
    0.55
     kasarigan
    0.52
     tranquillity
    0.50
     contradictions
    0.50
     destroyed
    0.50
     uſ
    0.50
    Act Density 0.192%

    No Known Activations