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

    Neuronpedia

    INDEX
    Explanations

    statements asserting an argument or position

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.70
    emis
    -0.67
    Tax
    -0.66
    WARD
    -0.65
    thro
    -0.63
    ctic
    -0.58
    Guard
    -0.58
    IDA
    -0.56
    "],"
    -0.55
    hips
    -0.55
    POSITIVE LOGITS
    soever
    0.77
    cher
    0.76
     culminated
    0.76
     lasted
    0.74
    ching
    0.71
    ched
    0.69
     same
    0.68
     mattered
    0.68
    ÅĤ
    0.67
    chers
    0.65
    Act Density 0.103%

    No Known Activations