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

    Neuronpedia

    INDEX
    Explanations

    mentions of actions involving sidestepping

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sid" or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.74
    ASED
    -0.62
     retard
    -0.62
    Ļ½
    -0.61
    姫
    -0.60
     Abyss
    -0.60
     UNESCO
    -0.59
     grandparents
    -0.59
     doomed
    -0.58
     magnets
    -0.57
    POSITIVE LOGITS
    eways
    1.38
    este
    1.38
    etr
    1.35
    emark
    1.11
    eworks
    1.05
    eline
    1.05
    eto
    1.04
    uction
    1.04
    uctive
    1.03
    emen
    1.02
    Act Density 0.036%

    No Known Activations