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

    Neuronpedia

    INDEX
    Explanations

    specific lines of code and programming terms

    oai_token-act-pair · gpt-3.5-turbo

    numeric and statistical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.68
    ikuman
    -0.67
     cafeteria
    -0.61
    ipeg
    -0.61
     Reloaded
    -0.54
    atown
    -0.54
    Ô
    -0.54
    ghai
    -0.53
     Disneyland
    -0.52
    idays
    -0.51
    POSITIVE LOGITS
     Obj
    0.63
     applied
    0.62
    Applic
    0.60
     apply
    0.58
     Applic
    0.57
     crochet
    0.57
     applicable
    0.55
    upper
    0.54
     phrases
    0.54
     "%
    0.53
    Act Density 1.214%

    No Known Activations