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

    Neuronpedia

    INDEX
    Explanations

    character names and their interactions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elan
    -0.15
    OMEM
    -0.15
    'gc
    -0.14
    Ấ
    -0.14
    ëĿ
    -0.14
    elf
    -0.14
    wer
    -0.14
    !=(
    -0.14
    ãĥ¬ãĥ¼
    -0.14
    %%%%%%%%
    -0.13
    POSITIVE LOGITS
    esson
    0.15
     intervening
    0.14
     refurbished
    0.14
    gmt
    0.14
    uesto
    0.14
    ’s
    0.14
    äm
    0.13
    BTN
    0.13
     overhe
    0.13
     wounds
    0.13
    Act Density 0.237%

    No Known Activations