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

    Neuronpedia

    INDEX
    Explanations

    praises or expressions of enthusiasm about experiences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldo
    -0.16
    opp
    -0.15
    echan
    -0.15
    ndx
    -0.14
    缤
    -0.14
    uner
    -0.14
    ÅĪ
    -0.14
    emez
    -0.13
    992
    -0.13
    زش
    -0.13
    POSITIVE LOGITS
    erg
    0.16
    CES
    0.15
    etto
    0.15
    à¹Ģลย
    0.15
    ago
    0.14
    ìħ
    0.14
     yat
    0.14
    brook
    0.14
    untu
    0.14
    odel
    0.14
    Act Density 0.323%

    No Known Activations