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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning physical movement or action

    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
    qua
    -0.76
    hetical
    -0.76
    ged
    -0.71
    iPhone
    -0.70
    BT
    -0.66
    iston
    -0.65
    vi
    -0.64
    jo
    -0.63
    ENS
    -0.61
    Sil
    -0.58
    POSITIVE LOGITS
     corners
    0.84
    atform
    0.83
     town
    0.80
    essage
    0.79
     freely
    0.78
    bilt
    0.75
    bag
    0.74
    bags
    0.72
    unin
    0.72
    anchester
    0.72
    Act Density 0.035%

    No Known Activations