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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values related to horsepower in motor vehicles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific horsepower values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nels
    -0.85
    nel
    -0.79
    querque
    -0.74
    odes
    -0.74
    pos
    -0.72
    abol
    -0.72
    lict
    -0.71
    oses
    -0.71
    liction
    -0.70
    chal
    -0.69
    POSITIVE LOGITS
     ILCS
    0.81
    mAh
    0.75
     MHz
    0.75
    itudinal
    0.74
    æ©Ł
    0.73
    989
    0.70
    tip
    0.65
    )</
    0.64
    799
    0.64
    MH
    0.63
    Act Density 0.022%

    No Known Activations