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

    Neuronpedia

    INDEX
    Explanations

    the word "But" as the common thread among the activations

    oai_token-act-pair · gpt-3.5-turbo

    the word "But" and its repeated use to introduce contrasting statements or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯
    -0.63
    ãģ®
    -0.61
    heads
    -0.60
    fell
    -0.60
    ().
    -0.59
     segment
    -0.58
    .","
    -0.57
    pointer
    -0.56
    built
    -0.55
    bound
    -0.54
    POSITIVE LOGITS
    tons
    1.24
    chers
    0.88
     alas
    0.86
    theless
    0.85
    withstanding
    0.82
    romeda
    0.81
    owsky
    0.77
    ts
    0.76
    LER
    0.76
    tif
    0.75
    Act Density 0.088%

    No Known Activations