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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "a" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ystone
    -0.18
    pad
    -0.17
    ilver
    -0.17
    nap
    -0.16
    dÄĽ
    -0.15
    gia
    -0.15
    ppo
    -0.15
    oretical
    -0.14
    cef
    -0.14
    annes
    -0.14
    POSITIVE LOGITS
    itm
    0.15
    .FontStyle
    0.14
    hover
    0.14
    aÄį
    0.14
    fort
    0.14
    sure
    0.14
    eel
    0.14
    istrat
    0.14
    ascar
    0.13
    ackers
    0.13
    Act Density 0.021%

    No Known Activations