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

    Neuronpedia

    INDEX
    Explanations

    expressions or actions of symbolic significance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gestures or symbolic actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ondo
    -0.76
    elsen
    -0.75
     Nightmares
    -0.71
    teen
    -0.69
    Mos
    -0.68
    gray
    -0.67
    IED
    -0.67
    ŀ
    -0.63
    gres
    -0.63
    aryl
    -0.63
    POSITIVE LOGITS
     gesture
    1.55
     gestures
    1.31
     towards
    0.97
     toward
    0.96
     swipe
    0.89
     salute
    0.86
     greeting
    0.84
     dexterity
    0.80
     recogn
    0.79
     glance
    0.77
    Act Density 0.021%

    No Known Activations