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

    Neuronpedia

    INDEX
    Explanations

    words related to action and physical movement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "action" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bey
    -0.70
    arton
    -0.69
    aye
    -0.68
    YL
    -0.68
    redit
    -0.66
    thening
    -0.65
    cott
    -0.65
     Petition
    -0.64
     Mead
    -0.64
    DAQ
    -0.61
    POSITIVE LOGITS
     scenes
    0.91
     sequences
    0.82
    fighting
    0.80
     flick
    0.78
     hero
    0.77
     unfold
    0.76
    movie
    0.76
    packed
    0.75
    hero
    0.75
     movie
    0.74
    Act Density 0.035%

    No Known Activations