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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hands-on activities or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to hands-on activities or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Swordsman
    -0.68
     Brush
    -0.67
     Pell
    -0.66
    ITION
    -0.65
     Polo
    -0.65
     Coat
    -0.63
     Fallon
    -0.63
     Jacket
    -0.62
     Pearl
    -0.62
     Dickinson
    -0.61
    POSITIVE LOGITS
    everal
    1.03
    only
    1.00
    sembly
    0.91
    inspired
    0.90
    based
    0.87
    uper
    0.86
    conservancy
    0.86
    ettings
    0.85
    rights
    0.85
    forward
    0.85
    Act Density 0.066%

    No Known Activations