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

    Neuronpedia

    INDEX
    Explanations

    conjunctive phrases that indicate contrast or negation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     elä
    -0.57
     lemmas
    -0.56
     onely
    -0.52
     colpa
    -0.50
     obiet
    -0.48
     löytyy
    -0.48
     retreats
    -0.48
     οδ
    -0.48
     bílé
    -0.48
     superiors
    -0.47
    POSITIVE LOGITS
    __':
    0.65
    Pyx
    0.64
    íritu
    0.63
    Aiheesta
    0.61
     calendriers
    0.60
     <<<<<<<<<<<<<<
    0.59
    __':
    0.58
    NUMX
    0.57
    +");
    0.57
    تقاوى
    0.57
    Act Density 0.062%

    No Known Activations