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

    Neuronpedia

    INDEX
    Explanations

    programming-related elements, particularly function calls and method names in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isible
    -0.56
    pédie
    -0.55
    __((
    -0.54
    ful
    -0.53
     كمان
    -0.52
     елның
    -0.52
     بيها
    -0.50
     omt
    -0.49
    pezi
    -0.48
    ubourg
    -0.48
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.85
    cat
    0.79
    cats
    0.74
    Cat
    0.68
     cat
    0.68
    cektir
    0.68
     Meksiku
    0.68
     cats
    0.67
    Cats
    0.66
    ynb
    0.66
    Act Density 2.086%

    No Known Activations