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

    Neuronpedia

    INDEX
    Explanations

    situations involving conflict or confrontation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     craters
    -0.63
    Statistiche
    -0.60
     kasarigan
    -0.59
     @"/
    -0.58
     thrones
    -0.57
     twain
    -0.57
     betweenstory
    -0.57
    habits
    -0.56
    roned
    -0.55
     vertes
    -0.55
    POSITIVE LOGITS
    inthians
    0.52
    énez
    0.48
     تعدى
    0.47
     teria
    0.47
    requireNonNull
    0.46
    >*/
    0.46
     fe
    0.46
     pior
    0.46
    higan
    0.45
    bolo
    0.45
    Act Density 0.338%

    No Known Activations