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

    Neuronpedia

    INDEX
    Explanations

    words related to discussing or criticizing topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "disc" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.77
    glers
    -0.75
    mberg
    -0.74
    tti
    -0.73
    cki
    -0.71
    akeru
    -0.69
    externalActionCode
    -0.69
    gio
    -0.68
    VILLE
    -0.65
    ahime
    -0.64
    POSITIVE LOGITS
    ussions
    1.32
    overed
    1.23
    ussion
    1.14
    ussed
    1.13
    iple
    1.12
    ourse
    1.12
    ount
    1.10
    ontent
    1.07
    retion
    1.06
    rete
    0.97
    Act Density 0.020%

    No Known Activations