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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arkin
    -0.16
    mund
    -0.16
    aza
    -0.15
    orig
    -0.15
    recated
    -0.14
    _snd
    -0.14
    beck
    -0.14
    sak
    -0.13
    ennent
    -0.13
    eday
    -0.13
    POSITIVE LOGITS
    ports
    0.15
    erg
    0.15
    rack
    0.15
    caffold
    0.15
     بÙĪابة
    0.14
     ANSI
    0.13
    gebn
    0.13
    \Base
    0.13
    .Safe
    0.13
    ingham
    0.13
    Act Density 0.010%

    No Known Activations