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

    Neuronpedia

    INDEX
    Explanations

    negative sentiments or contrasting comparisons in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zug
    -0.16
    untime
    -0.15
    ære
    -0.14
    fax
    -0.14
    _codegen
    -0.14
     synth
    -0.14
     åĺ
    -0.14
    zilla
    -0.14
    Ñĩе
    -0.14
    curring
    -0.14
    POSITIVE LOGITS
    igid
    0.16
    ,↵
    0.15
    egg
    0.15
    asp
    0.15
    pest
    0.14
    å°¾
    0.14
    inden
    0.14
    ac
    0.13
     emb
    0.13
    readcr
    0.13
    Act Density 0.881%

    No Known Activations