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

    Neuronpedia

    INDEX
    Explanations

    terms related to worst-case scenarios and contrasting conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _rwlock
    -0.15
     Sunder
    -0.15
    auga
    -0.14
    Smarty
    -0.13
    spam
    -0.13
    SystemService
    -0.13
     Sylv
    -0.13
    à¹Īà¸Ń
    -0.13
    éĬ·
    -0.12
    ColumnsMode
    -0.12
    POSITIVE LOGITS
     Sc
    0.96
    -sc
    0.95
    sc
    0.93
    Sc
    0.93
     sc
    0.90
     SC
    0.90
    _sc
    0.88
    .sc
    0.85
    SC
    0.82
    .Sc
    0.82
    Act Density 0.270%

    No Known Activations