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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "plus" accompanied by specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "plus" and its variations, indicating an additive or cumulative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dfx
    -0.81
    ruary
    -0.75
    adr
    -0.71
    ugu
    -0.71
    OCK
    -0.69
    utable
    -0.67
    ollar
    -0.66
    clinton
    -0.66
    abies
    -0.65
    NPR
    -0.65
    POSITIVE LOGITS
    cules
    1.02
    minus
    0.88
     bonuses
    0.75
     bonus
    0.74
    henko
    0.74
    /-
    0.73
     infinity
    0.72
     extras
    0.69
    lihood
    0.68
     assorted
    0.65
    Act Density 0.033%

    No Known Activations