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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific research and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "This" indicating new ideas or concepts introduced in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARS
    -0.77
    unk
    -0.76
    aws
    -0.71
    amia
    -0.67
    icons
    -0.64
    adle
    -0.63
    oller
    -0.63
    rums
    -0.63
    isms
    -0.61
    own
    -0.61
    POSITIVE LOGITS
     latter
    0.89
     contrasts
    0.86
     article
    0.83
     arrang
    0.83
     culminated
    0.82
     discrepancy
    0.81
     particular
    0.80
     trope
    0.80
     week
    0.79
     phenomenon
    0.78
    Act Density 0.163%

    No Known Activations