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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy and user account settings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ತ್ತು
    -0.69
     ВО
    -0.67
    repres
    -0.65
    GenerationType
    -0.65
     Calla
    -0.63
     Jen
    -0.61
     Schwe
    -0.61
     Dall
    -0.61
    czegó
    -0.60
     Scho
    -0.59
    POSITIVE LOGITS
    expandindo
    0.76
    وردار
    0.68
     atlik
    0.65
    ய்ய
    0.63
    UVWXYZ
    0.63
    riwal
    0.62
    UAWEI
    0.62
    }{*}{
    0.60
    енча
    0.60
     ZS
    0.59
    Act Density 0.011%

    No Known Activations