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

    Neuronpedia

    INDEX
    Explanations

    words related to actions involving preparation

    oai_token-act-pair · gpt-3.5-turbo

    words related to preparation for events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.75
    =-=-=-=-=-=-=-=-
    -0.66
    ILA
    -0.64
    rored
    -0.63
    ignment
    -0.63
    lished
    -0.62
    ĸļ
    -0.62
    rylic
    -0.62
    orph
    -0.61
    elected
    -0.61
    POSITIVE LOGITS
     for
    1.04
     beforehand
    0.97
     accordingly
    0.89
    NESS
    0.88
    ness
    0.82
     ahead
    0.78
     meals
    0.74
     contingency
    0.74
     defences
    0.74
     FOR
    0.71
    Act Density 0.052%

    No Known Activations