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

    Neuronpedia

    INDEX
    Explanations

    instances of multiple asterisks, indicating emphasis or importance in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.14
    al
    -0.14
    его
    -0.14
    eline
    -0.14
    raf
    -0.13
    rc
    -0.13
    ³
    -0.13
    tet
    -0.13
    andbox
    -0.13
    iciary
    -0.13
    POSITIVE LOGITS
    ácil
    0.17
    ouser
    0.16
    amik
    0.16
    isque
    0.15
    ĥn
    0.15
    odash
    0.15
    .undefined
    0.14
    mh
    0.14
    itol
    0.14
    isbury
    0.13
    Act Density 0.026%

    No Known Activations