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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or action involving physical space

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "around"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hetical
    -0.79
    qua
    -0.75
    vi
    -0.71
    ged
    -0.70
    iPhone
    -0.69
    igh
    -0.67
    jo
    -0.67
    IJ
    -0.66
    Sent
    -0.66
    andre
    -0.66
    POSITIVE LOGITS
     corners
    1.00
     town
    0.95
    town
    0.77
     freely
    0.76
     uncontroll
    0.70
    bag
    0.69
    luster
    0.67
    bags
    0.67
     nervously
    0.67
     frantically
    0.66
    Act Density 0.048%

    No Known Activations