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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'g'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tk
    -0.16
    oogle
    -0.15
    DEST
    -0.14
     Blow
    -0.14
    oles
    -0.14
     Disp
    -0.14
    imest
    -0.14
    dest
    -0.14
     Sole
    -0.14
    sten
    -0.13
    POSITIVE LOGITS
    estic
    0.26
    azing
    0.21
    idd
    0.20
    iddy
    0.20
    ird
    0.20
    hou
    0.19
    urg
    0.19
    ingham
    0.19
    awk
    0.18
    rooms
    0.18
    Act Density 0.026%

    No Known Activations