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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the importance of various actions or considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the significance of certain statements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILA
    -0.74
    uthor
    -0.73
    ãĤ¦ãĤ¹
    -0.66
     Carbuncle
    -0.63
     Ended
    -0.62
    opoly
    -0.61
    urus
    -0.59
    favorite
    -0.57
    bare
    -0.56
    ãĤ´ãĥ³
    -0.56
    POSITIVE LOGITS
     that
    0.96
     to
    0.89
     enough
    0.80
     for
    0.80
     nonetheless
    0.76
     we
    0.74
     lest
    0.69
    that
    0.66
    expr
    0.65
     not
    0.64
    Act Density 0.070%

    No Known Activations