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

    Neuronpedia

    INDEX
    Explanations

    HTML elements commonly used for form elements and interactive components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Classes
    -0.77
     subclasses
    -0.67
    Classes
    -0.65
    classes
    -0.61
    CLASSES
    -0.60
     CLASSES
    -0.56
    GenerationType
    -0.56
    Classe
    -0.55
     Classe
    -0.55
    enderror
    -0.52
    POSITIVE LOGITS
     cla
    0.60
     Clar
    0.57
     claus
    0.56
     classic
    0.55
    Erreferentziak
    0.53
     cl
    0.50
     clar
    0.50
     CLAR
    0.49
    \{\\
    0.47
     claw
    0.47
    Act Density 0.109%

    No Known Activations