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

    Neuronpedia

    INDEX
    Explanations

    words related to discussions or debates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "disc" or similar variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.77
    cki
    -0.77
    aukee
    -0.75
    tti
    -0.71
    ettings
    -0.65
     deed
    -0.64
    gio
    -0.63
    DF
    -0.62
    Downloadha
    -0.61
    ħĭ
    -0.61
    POSITIVE LOGITS
    ussions
    1.19
    ourse
    1.08
    overed
    1.08
    rim
    1.07
    ontent
    1.06
    ourses
    1.05
    ount
    1.04
    ussed
    1.04
    ont
    1.00
    rep
    0.98
    Act Density 0.009%

    No Known Activations