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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 'G' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sume
    -0.15
    uky
    -0.14
    aysia
    -0.14
    pery
    -0.14
    itous
    -0.14
    sembly
    -0.14
    dehyde
    -0.14
    ãĥ¼ãĤ¿
    -0.14
    tics
    -0.14
    tical
    -0.14
    POSITIVE LOGITS
    orman
    0.31
    lick
    0.30
    iese
    0.29
    ould
    0.28
    omes
    0.28
    arc
    0.27
    allow
    0.27
    artner
    0.27
    agli
    0.27
    omez
    0.26
    Act Density 0.031%

    No Known Activations