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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence of a strong emotional experience or sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Moran
    -0.15
    ů
    -0.15
    ippo
    -0.14
     polygon
    -0.14
    chai
    -0.13
     Morm
    -0.13
    lectual
    -0.13
     McGu
    -0.13
    rb
    -0.13
    ел
    -0.13
    POSITIVE LOGITS
    Scalar
    0.16
    zent
    0.15
    ruba
    0.14
    Å¡ov
    0.14
    305
    0.14
    rij
    0.14
     midd
    0.14
    ckill
    0.13
    _relations
    0.13
     mappedBy
    0.13
    Act Density 0.114%

    No Known Activations