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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the sound "hu" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cloth
    -0.65
    spin
    -0.63
     totality
    -0.62
    prints
    -0.62
    look
    -0.62
     Dispatch
    -0.62
     Balance
    -0.61
    lining
    -0.60
    race
    -0.60
     greens
    -0.60
    POSITIVE LOGITS
    awei
    1.53
    isine
    1.05
    pling
    0.93
    izen
    0.92
    gey
    0.91
    itsu
    0.89
    ilty
    0.87
    ahah
    0.87
    pta
    0.87
    pload
    0.85
    Act Density 0.013%

    No Known Activations