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

    Neuronpedia

    INDEX
    Explanations

    numerical values or parameters related to coding and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    riad
    -0.08
    ssa
    -0.08
    affen
    -0.08
    umas
    -0.07
    861
    -0.07
    gili
    -0.07
    lij
    -0.07
    awan
    -0.07
    arest
    -0.07
    rawn
    -0.07
    POSITIVE LOGITS
    ing
    0.07
    ox
    0.06
    arial
    0.06
    .depend
    0.06
     silence
    0.06
    nem
    0.06
    sil
    0.06
    mods
    0.06
     correspondence
    0.06
    _defs
    0.06
    Act Density 0.019%

    No Known Activations