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

    Neuronpedia

    INDEX
    Explanations

    website or software development-related technical terms

    oai_token-act-pair · gpt-3.5-turbo

    periods and numbers within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boarding
    -0.68
    cheon
    -0.67
     shells
    -0.65
    nets
    -0.62
     wedd
    -0.62
    culosis
    -0.61
     lang
    -0.61
    ouver
    -0.60
    lees
    -0.58
     lion
    -0.57
    POSITIVE LOGITS
    024
    0.78
    Cola
    0.77
    237
    0.75
     Centauri
    0.72
    200
    0.72
    920
    0.71
    ĨĴ
    0.68
    800
    0.68
    776
    0.68
    small
    0.67
    Act Density 0.129%

    No Known Activations