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

    Neuronpedia

    INDEX
    Explanations

    connections and references to other subjects or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DockStyle
    -1.07
     leſs
    -0.77
    esModule
    -0.77
     pleaſure
    -0.77
     juſ
    -0.73
     ſtre
    -0.72
     houſe
    -0.71
     poffe
    -0.69
     ―――――
    -0.69
     uſe
    -0.68
    POSITIVE LOGITS
     continúas
    0.60
    <bos>
    0.54
     pesky
    0.54
     '
    0.53
    Regarding
    0.52
    Về
    0.51
    évaluateur
    0.51
    关于
    0.50
    стви
    0.48
     Thomas
    0.48
    Act Density 0.060%

    No Known Activations