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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something happening frequently or repeatedly

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "too often" or similar expressions indicating frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.72
    anmar
    -0.72
    gewater
    -0.72
    andan
    -0.69
    utenberg
    -0.68
    sterdam
    -0.67
    kind
    -0.67
    gur
    -0.67
    =]
    -0.67
    shi
    -0.66
    POSITIVE LOGITS
    entimes
    1.19
    theless
    0.87
     encountered
    0.85
     msec
    0.84
     Asked
    0.84
     times
    0.83
     overlooked
    0.82
    è¦ļéĨĴ
    0.78
    Used
    0.76
    times
    0.76
    Act Density 0.026%

    No Known Activations