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

    Neuronpedia

    INDEX
    Explanations

    words related to movement and actions

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.72
    lain
    -0.66
    ament
    -0.63
    ullah
    -0.62
    icipated
    -0.61
    creen
    -0.61
    inelli
    -0.61
    ellation
    -0.59
    Lat
    -0.59
    eers
    -0.57
    POSITIVE LOGITS
     overboard
    1.01
     limp
    0.97
    lems
    0.94
    vt
    0.92
     nuts
    0.89
     ballistic
    0.89
     viral
    0.88
    ggle
    0.85
     numb
    0.84
     crazy
    0.84
    Act Density 0.111%

    No Known Activations