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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the expression "in short" or similar phrases that summarize a concept

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize a point or provide restatement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¥
    -0.71
    Äĩ
    -0.70
    alysed
    -0.68
    aq
    -0.67
    col
    -0.64
    Rated
    -0.63
    REAM
    -0.61
    gi
    -0.61
    rals
    -0.61
    igators
    -0.60
    POSITIVE LOGITS
    yss
    0.88
     unless
    0.75
     beware
    0.70
     imagine
    0.68
     yeah
    0.65
     congratulations
    0.65
    ymm
    0.64
     Whoever
    0.64
     whoever
    0.63
     barring
    0.63
    Act Density 0.082%

    No Known Activations