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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that indicate emotional responses or significant concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     åķĨ
    -0.16
    opsis
    -0.16
    åķĨ
    -0.16
    ruk
    -0.15
     sor
    -0.15
    ono
    -0.14
    çŃĴ
    -0.14
    [strlen
    -0.14
    assin
    -0.13
    wap
    -0.13
    POSITIVE LOGITS
    agner
    0.17
    erra
    0.16
    odyn
    0.15
    odian
    0.14
     Hlav
    0.14
    dash
    0.14
     League
    0.14
    oÄį
    0.14
    aga
    0.13
    achs
    0.13
    Act Density 0.001%

    No Known Activations