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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transition phrases that introduce additional information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Mention
    -0.49
    argate
    -0.49
    ukes
    -0.48
    ScreenState
    -0.48
     pool
    -0.47
    さい
    -0.47
    ArrowToggle
    -0.47
    ceous
    -0.47
    ask
    -0.46
    alt
    -0.45
    POSITIVE LOGITS
     itſelf
    0.69
     Vikipedi
    0.68
     theſe
    0.66
     pleaſure
    0.65
     >=",
    0.65
    setVerticalGroup
    0.63
     myſelf
    0.62
     BoxDecoration
    0.62
     خارجية
    0.61
    //
    0.61
    Act Density 0.030%

    No Known Activations