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

    Neuronpedia

    INDEX
    Explanations

    words related to revisions or changes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rev" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Story
    -0.73
     Tale
    -0.71
     charism
    -0.66
     Crate
    -0.65
     Superintendent
    -0.63
    lehem
    -0.63
    berman
    -0.63
    ãģ¦
    -0.62
     Neighbor
    -0.62
    lla
    -0.61
    POSITIVE LOGITS
    ulsion
    1.21
    ivals
    1.20
    ascular
    1.16
    olved
    1.11
    olve
    1.09
    amping
    1.07
    oking
    1.03
    isions
    1.00
    iving
    0.98
    ved
    0.98
    Act Density 0.008%

    No Known Activations