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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and other connecting words that indicate relationships or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellij
    -0.15
     Void
    -0.15
    .ObjectMeta
    -0.14
    lamaz
    -0.13
     Marcel
    -0.13
    ätz
    -0.13
    ("'"
    -0.13
    inden
    -0.13
     «
    -0.13
    pu
    -0.12
    POSITIVE LOGITS
    airy
    0.15
    997
    0.15
    041
    0.15
     Sanity
    0.14
    raquo
    0.14
    pta
    0.14
    ddb
    0.14
    795
    0.14
    ehir
    0.13
    Ctrls
    0.13
    Act Density 0.050%

    No Known Activations