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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a decision or conclusion being made

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to determining possibilities or making judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.80
    rious
    -0.72
    ãĥ¼ãĥĨãĤ£
    -0.71
    ufact
    -0.70
    intage
    -0.68
    apest
    -0.67
    ription
    -0.66
     Pastebin
    -0.65
     ILCS
    -0.65
    ickr
    -0.65
    POSITIVE LOGITS
     out
    0.88
     against
    0.79
     decisively
    0.78
    atively
    0.76
     differently
    0.74
     definitively
    0.73
    phas
    0.72
    maker
    0.65
    istically
    0.65
    orously
    0.64
    Act Density 0.046%

    No Known Activations