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

    Neuronpedia

    INDEX
    Explanations

    the word "it" often in sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to an object or item being discussed or used

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idth
    -0.66
    ãĥ©ãĥ³
    -0.60
     Polk
    -0.59
     Passenger
    -0.59
     Siege
    -0.58
     Frontier
    -0.58
     Car
    -0.57
    Band
    -0.57
    Priv
    -0.56
     Balloon
    -0.56
    POSITIVE LOGITS
    alian
    1.42
    self
    1.09
    unes
    1.08
    chy
    1.01
    atic
    1.01
    iner
    0.94
    ueller
    0.91
    atically
    0.83
    atical
    0.82
    alia
    0.78
    Act Density 0.199%

    No Known Activations