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

    Neuronpedia

    INDEX
    Explanations

    sequences related to the word "column" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    capitalization and specific formatting of the word "colleges" or similar structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idays
    -0.76
    thodox
    -0.75
    ramid
    -0.75
    Downloadha
    -0.72
    yip
    -0.68
    ausible
    -0.66
    ittance
    -0.66
    stood
    -0.65
    izons
    -0.65
    drm
    -0.65
    POSITIVE LOGITS
    houn
    0.74
    å°Ĩ
    0.74
    agues
    0.70
     Rasm
    0.67
    neck
    0.67
     Gillespie
    0.66
    ãĥ¢
    0.64
     Phillip
    0.62
     Rae
    0.62
    ipes
    0.62
    Act Density 0.096%

    No Known Activations