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

    Neuronpedia

    INDEX
    Explanations

    words related to confirmation or validation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     proof
    -0.71
    proof
    -0.68
     Clayton
    -0.63
     Rok
    -0.63
    Rok
    -0.62
     Barrios
    -0.62
     truth
    -0.61
     Peoria
    -0.61
     mulus
    -0.59
     little
    -0.58
    POSITIVE LOGITS
    دانشنامهٔ
    0.97
     MainAxisSize
    0.91
     velkommen
    0.88
    aarrggbb
    0.87
    fpm
    0.86
     незавершена
    0.86
    ControllerAdvice
    0.85
    UserScript
    0.85
    BeginInit
    0.84
    /*
    0.84
    Act Density 0.018%

    No Known Activations