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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the beginning of actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the initiation of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.76
    dad
    -0.66
    bey
    -0.66
    acho
    -0.66
    model
    -0.66
    ided
    -0.65
    ides
    -0.64
    uably
    -0.64
    bent
    -0.62
     bearer
    -0.60
    POSITIVE LOGITS
     anew
    1.05
     airing
    0.83
     PRESS
    0.78
    ezvous
    0.74
     preparations
    0.74
    ional
    0.74
    OCK
    0.71
     Phase
    0.71
    odcast
    0.68
    OURCE
    0.67
    Act Density 0.077%

    No Known Activations