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

    Neuronpedia

    INDEX
    Explanations

    company announcements

    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
    EStream
    -0.76
    arse
    -0.72
    Thumbnail
    -0.71
    ãĤ©
    -0.70
     exting
    -0.66
    ptoms
    -0.65
    kamp
    -0.64
    ealous
    -0.63
    WAYS
    -0.62
    emate
    -0.62
    POSITIVE LOGITS
     they
    0.99
     there
    0.77
     although
    0.77
     we
    0.77
     "[
    0.69
     he
    0.68
     THEY
    0.67
     despite
    0.66
     indefinitely
    0.66
    soever
    0.65
    Act Density 0.155%

    No Known Activations