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

    Neuronpedia

    INDEX
    Explanations

    numeric values associated with software versioning or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ladu
    -0.17
    IGINAL
    -0.15
    oksen
    -0.15
    avou
    -0.14
    esson
    -0.14
    erate
    -0.14
    atchet
    -0.14
    iá»ģn
    -0.14
    avis
    -0.14
     Ih
    -0.14
    POSITIVE LOGITS
    997
    0.16
    ili
    0.16
    .x
    0.15
     Underground
    0.15
    rc
    0.15
    Ä©
    0.14
    _RC
    0.14
    .sz
    0.14
    .X
    0.14
     Selbst
    0.14
    Act Density 0.032%

    No Known Activations