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

    Neuronpedia

    INDEX
    Explanations

    information about updates and changes in content

    oai_token-act-pair · gpt-3.5-turbo

    content related to updates and information notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.67
     sacrific
    -0.60
     oun
    -0.60
     estab
    -0.59
    gio
    -0.58
     colle
    -0.57
     thous
    -0.54
     hog
    -0.53
    ij士
    -0.53
     Galile
    -0.53
    POSITIVE LOGITS
    felt
    0.66
    andr
    0.63
    ulnerability
    0.57
    piracy
    0.57
    hemy
    0.56
    ilver
    0.55
    stead
    0.55
    interstitial
    0.54
     categorized
    0.54
    APD
    0.54
    Act Density 0.027%

    No Known Activations