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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or probability of an event happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asar
    -0.68
    instead
    -0.67
     Sands
    -0.59
    urches
    -0.59
     Tanz
    -0.58
     Recording
    -0.57
     Tsukuyomi
    -0.56
    Afee
    -0.56
     Peninsula
    -0.55
     WRITE
    -0.54
    POSITIVE LOGITS
     importantly
    1.25
     likely
    1.21
     certainly
    1.14
     definitely
    1.13
     notably
    1.12
     assured
    1.08
    likely
    1.07
     prominently
    1.06
    afa
    1.02
     Likely
    0.97
    Act Density 0.041%

    No Known Activations