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

    Neuronpedia

    INDEX
    Explanations

    specific references to messages or news

    oai_token-act-pair · gpt-3.5-turbo

    recurring pronouns and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilial
    -0.65
    asionally
    -0.65
    amiya
    -0.63
    seek
    -0.61
    perture
    -0.60
    noon
    -0.59
    azon
    -0.58
    erness
    -0.58
    ibrary
    -0.58
     Tanz
    -0.57
    POSITIVE LOGITS
     traction
    0.89
    chy
    0.86
     foothold
    0.83
    retty
    0.78
     juices
    0.75
    oulos
    0.70
    started
    0.70
     bearings
    0.67
    yss
    0.65
     haircut
    0.64
    Act Density 0.123%

    No Known Activations