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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    references to others and comparisons with a collective experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urate
    -0.71
    forestation
    -0.69
    aceous
    -0.65
    Accessory
    -0.64
    acity
    -0.63
    tein
    -0.62
    Url
    -0.62
     Humane
    -0.61
    osterone
    -0.61
    oret
    -0.60
    POSITIVE LOGITS
    worldly
    0.97
     describ
    0.74
     else
    0.71
     who
    0.71
     besides
    0.71
     succumbed
    0.68
    mia
    0.68
     equally
    0.65
     nearby
    0.65
     afforded
    0.64
    Act Density 0.018%

    No Known Activations