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

    Neuronpedia

    INDEX
    Explanations

    phrases related to head gestures and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to physical gestures or movements of the head and arms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spir
    -0.74
    nor
    -0.73
    ipl
    -0.64
     Soph
    -0.62
    gor
    -0.62
    vacc
    -0.60
    updated
    -0.59
    ãĥĪ
    -0.58
     Weather
    -0.56
    veh
    -0.55
    POSITIVE LOGITS
     awkwardly
    0.69
     elsewhere
    0.68
    oots
    0.65
    acles
    0.65
    selves
    0.65
     beads
    0.65
     embargo
    0.64
    acle
    0.63
     politely
    0.63
    ounty
    0.63
    Act Density 0.105%

    No Known Activations