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

    Neuronpedia

    INDEX
    Explanations

    proper nouns that are names or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zer
    -0.17
    iaux
    -0.16
    ffset
    -0.16
    ваннÑı
    -0.15
    ical
    -0.15
    er
    -0.15
    gfx
    -0.15
    ically
    -0.15
    άÏģ
    -0.15
    ica
    -0.14
    POSITIVE LOGITS
    starter
    0.23
    ety
    0.22
    les
    0.19
    ening
    0.18
    nowledge
    0.18
    elson
    0.18
    ileaks
    0.17
    ledon
    0.17
    lesh
    0.17
    tion
    0.17
    Act Density 0.036%

    No Known Activations