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

    Neuronpedia

    INDEX
    Explanations

    references to current situations or time period

    oai_token-act-pair · gpt-3.5-turbo

    references to the current time or present circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.74
    later
    -0.66
    nce
    -0.64
    aud
    -0.64
    MAT
    -0.63
    STDOUT
    -0.60
     Parables
    -0.59
    gypt
    -0.58
    rophic
    -0.57
    Walk
    -0.57
    POSITIVE LOGITS
    abouts
    1.18
    tics
    0.82
    here
    0.69
    adays
    0.68
    女
    0.67
     underway
    0.67
    .
    0.65
    tical
    0.65
    ,
    0.64
    ,...
    0.63
    Act Density 0.077%

    No Known Activations