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

    Neuronpedia

    INDEX
    Explanations

    timestamps denoted in the format of "hour:minute a.m./p.m."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "m" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behav
    -0.78
     giveaway
    -0.65
     giveaways
    -0.62
     ãĤµ
    -0.61
     restruct
    -0.61
     Nebula
    -0.61
     smells
    -0.59
     Spice
    -0.59
    redo
    -0.58
     Vik
    -0.58
    POSITIVE LOGITS
    obiles
    1.07
    obile
    0.95
    igr
    0.90
    endment
    0.89
    otive
    0.88
    ansion
    0.84
    ISSION
    0.84
    otor
    0.83
    ortal
    0.80
    obil
    0.79
    Act Density 0.019%

    No Known Activations