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

    Neuronpedia

    INDEX
    Explanations

    phrases related to individual agency or actions taken independently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "themselves."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pour
    -0.74
     Derby
    -0.73
    ammy
    -0.72
    rise
    -0.71
    von
    -0.65
    mare
    -0.65
    yip
    -0.64
    ulu
    -0.64
     Surge
    -0.64
    grade
    -0.64
    POSITIVE LOGITS
     selves
    1.06
    selves
    1.04
     underwater
    0.78
    pecially
    0.77
     creatively
    0.72
     respective
    0.71
     themselves
    0.71
     fict
    0.70
    BOOK
    0.70
    å
    0.70
    Act Density 0.037%

    No Known Activations