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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-reflection and questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.67
    parsedMessage
    -0.63
     يتيمه
    -0.60
     TextAppearance
    -0.59
     protoimpl
    -0.56
    Datuak
    -0.56
     referenties
    -0.55
     ویکی‌پدیا
    -0.54
    Microkernel
    -0.54
    oredCriteria
    -0.53
    POSITIVE LOGITS
     stupid
    2.09
     dumb
    2.02
     stupidity
    1.86
     Stupid
    1.82
    stupid
    1.79
     foolish
    1.78
    Stupid
    1.75
     idiot
    1.74
     idiotic
    1.73
     silly
    1.62
    Act Density 0.694%

    No Known Activations