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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of features or attributes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assin
    -0.16
    arin
    -0.15
    elerik
    -0.15
     (('
    -0.14
     Lug
    -0.14
    RG
    -0.14
    .WriteAll
    -0.14
    EventArgs
    -0.14
    UST
    -0.14
     {{--<
    -0.14
    POSITIVE LOGITS
     prominently
    0.24
    lah
    0.17
     lots
    0.16
     fewer
    0.15
     a
    0.15
    ajs
    0.15
     elements
    0.15
    ué
    0.15
     among
    0.14
    :↵
    0.14
    Act Density 0.030%

    No Known Activations