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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "There is" or "There are"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "There is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprom
    -0.70
    natureconservancy
    -0.68
    ãĤĬ
    -0.58
     Throne
    -0.57
     IPM
    -0.56
    HAM
    -0.55
     Seym
    -0.54
     respons
    -0.53
     IMP
    -0.53
     Toast
    -0.52
    POSITIVE LOGITS
    after
    1.42
    upon
    1.20
    abouts
    1.11
    by
    1.05
     are
    1.03
    fore
    1.00
    FORE
    0.93
    in
    0.89
    ported
    0.88
    for
    0.88
    Act Density 0.105%

    No Known Activations