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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appen
    -0.18
    them
    -0.17
    好ãģį
    -0.16
    ynchronously
    -0.15
    erk
    -0.14
    aso
    -0.14
    orp
    -0.14
    agas
    -0.14
    _RATIO
    -0.14
    enor
    -0.14
    POSITIVE LOGITS
    lessly
    0.36
     they
    0.23
     someday
    0.23
    fulness
    0.23
    fully
    0.22
     none
    0.22
    FULL
    0.22
     soon
    0.21
     it
    0.21
     ferv
    0.21
    Act Density 0.027%

    No Known Activations