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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing intensity or quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing strong emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARM
    -0.71
    kick
    -0.68
    ertodd
    -0.66
     Lobby
    -0.63
    olate
    -0.63
    orial
    -0.63
    ntil
    -0.61
    achus
    -0.61
    EP
    -0.61
     Drum
    -0.59
    POSITIVE LOGITS
    ties
    0.76
    ities
    0.67
     abundantly
    0.65
    atan
    0.61
     specificity
    0.61
    tons
    0.60
    things
    0.60
    thing
    0.60
     Takeru
    0.59
     minded
    0.58
    Act Density 0.052%

    No Known Activations