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

    Neuronpedia

    INDEX
    Explanations

    instances where something is noticeable or observable

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing clarity or obviousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zanne
    -0.66
    mbuds
    -0.65
     tightly
    -0.63
    aird
    -0.63
     hired
    -0.62
     contracted
    -0.61
    nan
    -0.60
    reditary
    -0.60
     palms
    -0.59
     trained
    -0.58
    POSITIVE LOGITS
    iary
    1.42
     Signs
    0.90
    ial
    0.89
    ively
    0.87
    aneously
    0.87
    iator
    0.83
    iated
    0.82
    iveness
    0.80
    ible
    0.78
    ially
    0.76
    Act Density 0.018%

    No Known Activations