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

    Neuronpedia

    INDEX
    Explanations

    references to time in relation to an action or status

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ow"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     circulate
    -0.67
    ãĤ¶
    -0.66
     gratification
    -0.66
     apartheid
    -0.66
    ãĥ¼ãĥĨ
    -0.64
     Schwar
    -0.64
    ority
    -0.62
     pinch
    -0.60
    udes
    -0.60
     Rouge
    -0.59
    POSITIVE LOGITS
    OW
    1.17
    ARDS
    1.10
    ERS
    1.08
    LAN
    1.06
    orld
    1.04
    OWS
    1.02
    DER
    1.01
    HEAD
    1.00
    IE
    0.97
    ING
    0.95
    Act Density 0.006%

    No Known Activations