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

    Neuronpedia

    INDEX
    Explanations

    locations or destinations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating action or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.84
     gobl
    -0.78
    使
    -0.76
    onson
    -0.71
     Briggs
    -0.71
    ©¶æ¥µ
    -0.71
     Gord
    -0.70
    padding
    -0.69
    Rocket
    -0.69
    estic
    -0.69
    POSITIVE LOGITS
     WATCH
    1.64
     SEE
    1.60
     watch
    1.50
     Watch
    1.50
    Watch
    1.37
     VIEW
    1.36
     watches
    1.32
     watched
    1.31
    watch
    1.30
     wat
    1.29
    Act Density 0.289%

    No Known Activations