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

    Neuronpedia

    INDEX
    Explanations

    serious or impactful phrases

    oai_token-act-pair · gpt-3.5-turbo

    assertions and references to popular preferences or trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingly
    -0.58
    IOR
    -0.53
    fully
    -0.53
    ibly
    -0.51
    urized
    -0.51
    orable
    -0.51
    istries
    -0.50
    FUL
    -0.50
    ible
    -0.49
    mable
    -0.48
    POSITIVE LOGITS
    anwhile
    0.53
    iqueness
    0.53
     rounding
    0.44
    umo
    0.44
    ccoli
    0.43
     [+]
    0.43
    timer
    0.42
     contention
    0.42
    commit
    0.41
    ider
    0.41
    Act Density 0.748%

    No Known Activations