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

    Neuronpedia

    INDEX
    Explanations

    the word "there" followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "there" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fridays
    -0.68
     oats
    -0.63
    full
    -0.57
     Stras
    -0.57
     Mecca
    -0.56
     CJ
    -0.56
    ONSORED
    -0.55
     beans
    -0.55
    EStreamFrame
    -0.55
     whichever
    -0.55
    POSITIVE LOGITS
    abouts
    1.18
    upon
    0.94
    fore
    0.78
    olkien
    0.73
    ĩ
    0.73
    oplan
    0.73
    onian
    0.72
    ales
    0.69
     exists
    0.68
    ensibly
    0.64
    Act Density 0.079%

    No Known Activations