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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or physical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "lim" and its variations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     storm
    -0.60
     Wrath
    -0.60
     fasc
    -0.60
     fear
    -0.59
     havoc
    -0.59
     pleasure
    -0.59
    WR
    -0.58
     behold
    -0.57
     knots
    -0.57
     knowing
    -0.57
    POSITIVE LOGITS
    elight
    1.56
    erick
    1.37
    itations
    1.36
    estone
    1.27
    iter
    1.19
    ping
    1.12
    itation
    1.11
    bers
    1.10
    bered
    1.10
    estones
    1.08
    Act Density 0.037%

    No Known Activations