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

    Neuronpedia

    INDEX
    Explanations

    statements related to likelihood or probability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or likelihood about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lear
    -0.73
    acc
    -0.69
     Soph
    -0.65
     Truth
    -0.64
     WARNING
    -0.62
     hygiene
    -0.62
     Knowledge
    -0.62
     FAC
    -0.59
     Gab
    -0.59
     literacy
    -0.59
    POSITIVE LOGITS
     sooner
    1.06
     renegoti
    0.84
     relocate
    0.83
    morrow
    0.81
    soDeliveryDate
    0.81
     someday
    0.79
     reintrodu
    0.76
     revisit
    0.76
     bump
    0.75
     revert
    0.74
    Act Density 0.528%

    No Known Activations