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

    Neuronpedia

    INDEX
    Explanations

    phrases where someone is pointing something out

    oai_token-act-pair · gpt-3.5-turbo

    phrases or instances where someone is making a point

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.76
    wake
    -0.73
    asus
    -0.73
    ogn
    -0.69
    awar
    -0.65
    ophy
    -0.64
    blood
    -0.64
    culation
    -0.63
     tyr
    -0.63
     oun
    -0.63
    POSITIVE LOGITS
    wards
    0.83
     loopholes
    0.77
    rers
    0.72
     how
    0.72
    pad
    0.70
    rer
    0.68
     Amendments
    0.66
    iasis
    0.66
    ances
    0.64
    fitted
    0.63
    Act Density 0.017%

    No Known Activations