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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "there"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "there" and pronouns associated with a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.80
    Edge
    -0.66
     Mania
    -0.64
    ACY
    -0.64
    [[
    -0.64
    agna
    -0.63
    igo
    -0.61
    fty
    -0.61
    ERY
    -0.61
    reality
    -0.61
    POSITIVE LOGITS
    idges
    0.70
    along
    0.70
    ffield
    0.69
     uh
    0.65
    isSpecialOrderable
    0.65
     kindred
    0.64
     um
    0.63
    abouts
    0.62
     bases
    0.61
    soType
    0.61
    Act Density 0.137%

    No Known Activations