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

    Neuronpedia

    INDEX
    Explanations

    expressions related to urgency and departure

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ########.
    -0.74
     strdup
    -0.73
     Meksiku
    -0.71
    Datuak
    -0.67
    таратура
    -0.63
     couvert
    -0.62
     BoxDecoration
    -0.61
    jsonwebtoken
    -0.60
     betweenstory
    -0.59
     الحره
    -0.57
    POSITIVE LOGITS
     Verlags
    0.51
    </>
    0.48
    sedown
    0.43
    illeurs
    0.42
     MBA
    0.42
    本日は
    0.42
    CHELL
    0.42
     Appeal
    0.41
     katalog
    0.41
    Cats
    0.41
    Act Density 0.056%

    No Known Activations