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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific numerical values

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and indicators of emphasis or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascus
    -0.60
    eny
    -0.59
    ritz
    -0.57
     misunder
    -0.56
    nance
    -0.56
     oversaw
    -0.55
    phasis
    -0.55
    oÄŁan
    -0.54
     sanctioned
    -0.53
    tten
    -0.53
    POSITIVE LOGITS
     if
    1.91
    if
    1.75
     If
    1.67
    If
    1.53
     Otherwise
    1.47
    Otherwise
    1.44
     IF
    1.36
    else
    1.33
     endif
    1.21
    unless
    1.19
    Act Density 0.203%

    No Known Activations