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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases that indicate something remarkable or outside the norm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.17
    go
    -0.15
    isu
    -0.15
    roat
    -0.15
    ixin
    -0.14
    aved
    -0.14
    esh
    -0.14
    resco
    -0.14
    zilla
    -0.14
    ëł´
    -0.14
    POSITIVE LOGITS
    ordinary
    0.21
    -large
    0.17
     circumstances
    0.17
    üstü
    0.16
    CHIP
    0.15
     circumstance
    0.15
     atl
    0.15
    -looking
    0.15
    ordin
    0.15
    jal
    0.14
    Act Density 0.049%

    No Known Activations