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

    Neuronpedia

    INDEX
    Explanations

    emphasized physical movements or actions that convey a message or intention

    oai_token-act-pair · gpt-3.5-turbo

    references to gestures and symbolic actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondo
    -0.86
    src
    -0.75
    elsen
    -0.67
    aryl
    -0.67
    teen
    -0.66
    unker
    -0.65
    fortable
    -0.65
    sis
    -0.65
     Nightmares
    -0.65
    resident
    -0.64
    POSITIVE LOGITS
     gesture
    1.63
     gestures
    1.41
     salute
    0.88
     towards
    0.82
     recogn
    0.80
    ocene
    0.79
     Canaver
    0.77
    itives
    0.76
     toward
    0.74
     greeting
    0.73
    Act Density 0.007%

    No Known Activations