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

    Neuronpedia

    INDEX
    Explanations

    numerical values mixed with unit labels or text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to routes or paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.95
    vet
    -0.78
    vern
    -0.77
    creen
    -0.73
    forces
    -0.70
    akening
    -0.69
     shape
    -0.66
    ppa
    -0.66
    icago
    -0.65
     hunted
    -0.63
    POSITIVE LOGITS
    nm
    0.83
    625
    0.81
    40
    0.74
    %-
    0.74
    dfx
    0.73
    iary
    0.71
    480
    0.70
    %
    0.70
    345
    0.69
    765
    0.69
    Act Density 0.046%

    No Known Activations