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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate repetition or recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yst
    -0.18
    LLL
    -0.15
    .createComponent
    -0.14
    isin
    -0.14
     Coleman
    -0.14
    ITAL
    -0.14
     Tubes
    -0.14
    елÑĮзÑı
    -0.14
    ÑĪ
    -0.14
     CGAffineTransform
    -0.14
    POSITIVE LOGITS
    _DUMP
    0.16
    aise
    0.16
    rame
    0.15
    rij
    0.15
    icari
    0.15
    akening
    0.14
     abandon
    0.14
     annex
    0.14
    oir
    0.13
    RIX
    0.13
    Act Density 0.000%

    No Known Activations