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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms that indicate high quality or high value

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

    "high" preceding a characteristic

    np_acts-logits-general · gemini-2.0-flash

    high followed by specific descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    opsis
    -0.48
     Cordero
    -0.45
    oplan
    -0.45
    amante
    -0.43
     Beren
    -0.43
    batter
    -0.42
    trn
    -0.42
    makebox
    -0.41
    anatomy
    -0.41
    GeneratedCode
    -0.40
    POSITIVE LOGITS
     High
    1.08
     high
    1.08
    High
    1.02
     HIGH
    1.01
    high
    0.96
    HIGH
    0.89
     highest
    0.76
     Low
    0.75
     Highest
    0.75
    Highest
    0.74
    Act Density 0.224%

    No Known Activations