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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific actions or events

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "such" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertodd
    -0.86
    oil
    -0.78
    kick
    -0.76
    achus
    -0.74
    ocene
    -0.72
    icka
    -0.71
    emale
    -0.70
    ipedia
    -0.69
    pace
    -0.69
    ellen
    -0.68
    POSITIVE LOGITS
    ties
    0.78
     matters
    0.74
     heinous
    0.71
     amounts
    0.71
     drastic
    0.70
     kinds
    0.70
     establishments
    0.69
     mundane
    0.68
     sums
    0.67
    ities
    0.67
    Act Density 0.045%

    No Known Activations