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

    Neuronpedia

    INDEX
    Explanations

    specific points or moments in a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "one point" followed by numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enz
    -0.69
    Loading
    -0.62
    -+
    -0.60
    illed
    -0.60
    river
    -0.59
     naturally
    -0.59
    shed
    -0.58
    ^^^^
    -0.56
    wake
    -0.56
    DJ
    -0.56
    POSITIVE LOGITS
    anooga
    0.81
    oslov
    0.68
    xus
    0.64
     Osc
    0.63
     Fired
    0.62
    elfth
    0.62
    ulk
    0.62
     outburst
    0.61
     somew
    0.61
    Footnote
    0.60
    Act Density 0.048%

    No Known Activations