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

    Neuronpedia

    INDEX
    Explanations

    references to interviews and interviews' context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     haze
    -0.17
    iones
    -0.15
     deltas
    -0.15
    ical
    -0.15
    307
    -0.15
    erset
    -0.14
    weed
    -0.14
     McD
    -0.14
    _TOO
    -0.14
    tat
    -0.13
    POSITIVE LOGITS
    ÑģÑĤÑİ
    0.16
    riet
    0.15
    ongan
    0.15
    ¢åįķ
    0.15
    Latch
    0.15
    PY
    0.15
    /stdc
    0.14
    nds
    0.14
    specialchars
    0.14
    annt
    0.14
    Act Density 0.158%

    No Known Activations