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

    Neuronpedia

    INDEX
    Explanations

    references to software applications and their compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Forty
    -0.61
    Thirty
    -0.60
     Thirty
    -0.59
     Forty
    -0.59
    fifty
    -0.55
    autaire
    -0.55
     thirty
    -0.54
     Fifty
    -0.53
    thirty
    -0.53
     fifty
    -0.52
    POSITIVE LOGITS
     eleven
    0.74
     tenth
    0.69
     XI
    0.67
    Eleven
    0.67
     eleventh
    0.65
     ten
    0.65
    Twelve
    0.65
     XII
    0.64
     twelve
    0.63
    eleven
    0.63
    Act Density 0.804%

    No Known Activations