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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional states or experiences of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.17
    stro
    -0.16
     Lent
    -0.15
    aggio
    -0.15
    .Slice
    -0.15
    ÅŁa
    -0.15
    anford
    -0.14
    Resolution
    -0.14
     Berk
    -0.14
    ŀ
    -0.14
    POSITIVE LOGITS
    aku
    0.17
    akin
    0.16
     Ot
    0.15
    gmt
    0.14
    zt
    0.14
     Petr
    0.14
    itters
    0.13
    lay
    0.13
    Ot
    0.13
    ken
    0.13
    Act Density 0.013%

    No Known Activations