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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "There."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences starting with "There is" or "There was"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.63
     CJ
    -0.63
     cylinders
    -0.58
     ±
    -0.58
     cum
    -0.58
     nib
    -0.57
     Heights
    -0.57
     cup
    -0.57
     cogn
    -0.57
    ME
    -0.56
    POSITIVE LOGITS
    abouts
    1.50
    upon
    1.26
    after
    0.95
    fore
    0.94
    FORE
    0.85
    ngth
    0.82
    ibaba
    0.78
    idences
    0.76
    atility
    0.74
     guiActiveUn
    0.74
    Act Density 0.123%

    No Known Activations