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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eward
    -0.17
    inger
    -0.15
     Thrones
    -0.15
    ller
    -0.14
    acket
    -0.14
    icht
    -0.14
    izon
    -0.14
    ifton
    -0.13
    iper
    -0.13
    enger
    -0.13
    POSITIVE LOGITS
    inu
    0.16
    oreach
    0.14
    lbrace
    0.14
     Uncategorized
    0.14
    EPROM
    0.14
    ženÃŃ
    0.14
    .mods
    0.13
    oxic
    0.13
    deme
    0.13
    aired
    0.13
    Act Density 0.187%

    No Known Activations