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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @qq
    -0.15
    grund
    -0.15
    ously
    -0.14
    ny
    -0.14
    uele
    -0.14
    osity
    -0.14
    nat
    -0.13
    acht
    -0.13
    eon
    -0.13
    nick
    -0.13
    POSITIVE LOGITS
    ikk
    0.18
    ched
    0.18
    -Sah
    0.15
     same
    0.15
    ifa
    0.15
     Sexo
    0.15
    abouts
    0.15
     же
    0.14
     $$$
    0.14
    Ñĥки
    0.14
    Act Density 0.538%

    No Known Activations