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

    Neuronpedia

    INDEX
    Explanations

    terms associated with health, safety, and maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNUSED
    -0.17
    iverz
    -0.16
    ikon
    -0.15
     Holt
    -0.14
    _counters
    -0.14
    erken
    -0.14
    chio
    -0.14
    estr
    -0.14
    ols
    -0.14
    ÌĨ
    -0.14
    POSITIVE LOGITS
    entes
    0.16
    rani
    0.15
    ŀĭ
    0.14
     Functor
    0.14
    amura
    0.14
     tes
    0.14
     ado
    0.14
     Horizontal
    0.13
     Gig
    0.13
    alis
    0.13
    Act Density 0.019%

    No Known Activations