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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and legal controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pholes
    -0.54
    brigens
    -0.49
    towym
    -0.48
    TargetException
    -0.46
     volna
    -0.46
    ChildScrollView
    -0.45
     }}$}
    -0.44
    īg
    -0.44
    ATB
    -0.43
    inference
    -0.43
    POSITIVE LOGITS
    SourceChecksum
    0.90
     invokingState
    0.69
    principalColumn
    0.67
    ’
    0.65
     nakalista
    0.65
     himself
    0.63
    InitVars
    0.62
     announced
    0.61
     herself
    0.61
    RTDA
    0.59
    Act Density 0.405%

    No Known Activations