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

    Neuronpedia

    INDEX
    Explanations

    instances of authorship or speaking attribution in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omor
    -0.15
    ntl
    -0.15
    ç¨
    -0.15
     Dek
    -0.15
    oso
    -0.15
    uito
    -0.15
    ownt
    -0.15
    avou
    -0.14
    alis
    -0.14
    bum
    -0.14
    POSITIVE LOGITS
    endency
    0.17
    andles
    0.16
    rello
    0.16
    cox
    0.15
     tongue
    0.15
    .psi
    0.15
    ires
    0.15
    ugins
    0.15
    allery
    0.14
    -toggler
    0.14
    Act Density 0.011%

    No Known Activations