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

    Neuronpedia

    INDEX
    Explanations

    the word "so" in the text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "so" used to emphasize statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.60
    marks
    -0.58
    haven
    -0.57
    wreck
    -0.56
    work
    -0.56
    works
    -0.56
     presentation
    -0.54
    女
    -0.53
    INGTON
    -0.53
     customs
    -0.53
    POSITIVE LOGITS
    bered
    1.26
    oths
    1.20
    othes
    1.17
    apy
    1.05
    oner
    0.98
    othe
    0.97
    oooo
    0.95
    iled
    0.94
    ooo
    0.91
    aps
    0.89
    Act Density 0.115%

    No Known Activations