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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing potential actions and states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.16
    eland
    -0.15
    endale
    -0.15
    IFF
    -0.15
    asaki
    -0.15
     ç¢
    -0.14
    jian
    -0.14
    eli
    -0.14
    kop
    -0.14
    /releases
    -0.13
    POSITIVE LOGITS
     addCriterion
    0.15
     envelope
    0.14
    arsi
    0.14
    OnChange
    0.14
    oster
    0.14
    esinin
    0.14
     prox
    0.13
    رÙĥ
    0.13
     Mes
    0.13
    uma
    0.13
    Act Density 0.002%

    No Known Activations