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

    Neuronpedia

    INDEX
    Explanations

    the phrase "Not so"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "so" used to emphasize a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.70
    MAP
    -0.64
    é¾
    -0.61
     fixme
    -0.56
     outline
    -0.56
    imeters
    -0.56
    ãĤ¼ãĤ¦ãĤ¹
    -0.54
     MAP
    -0.53
     Places
    -0.53
    ayne
    -0.52
    POSITIVE LOGITS
     much
    0.87
    aked
    0.82
    oths
    0.77
    bered
    0.75
    zin
    0.73
    othes
    0.72
    imilar
    0.71
    oooo
    0.71
    oner
    0.69
    much
    0.69
    Act Density 0.037%

    No Known Activations