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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or assistance related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oct
    -0.15
    oog
    -0.14
     è»
    -0.14
     Valor
    -0.14
    awns
    -0.14
    ÏĥÏĦε
    -0.14
    omet
    -0.13
    à¹ĩà¸Ķ
    -0.13
    olland
    -0.13
    .Static
    -0.13
    POSITIVE LOGITS
    earable
    0.15
     rewards
    0.15
    ardy
    0.14
    HEMA
    0.14
    geh
    0.13
    leftright
    0.13
    974
    0.13
    è´¨éĩı
    0.13
     representation
    0.13
    irst
    0.13
    Act Density 0.048%

    No Known Activations