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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conflicts or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "full-blown" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.91
     Moreno
    -0.72
    imaru
    -0.72
    ubi
    -0.71
     Zar
    -0.71
     DRAG
    -0.69
     Springs
    -0.69
     Cah
    -0.69
     charms
    -0.68
     Richards
    -0.68
    POSITIVE LOGITS
    sized
    1.26
    bodied
    1.20
    function
    1.19
    level
    1.16
    eyed
    1.13
    fledged
    1.12
    season
    1.10
    class
    1.05
    contact
    1.04
    equipped
    1.03
    Act Density 0.044%

    No Known Activations