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

    Neuronpedia

    INDEX
    Explanations

    instances of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atte
    -0.18
    inke
    -0.16
    abant
    -0.16
    abee
    -0.15
    OnError
    -0.15
    Ỽ
    -0.14
    ois
    -0.14
    ostel
    -0.14
     Cush
    -0.14
    ehir
    -0.14
    POSITIVE LOGITS
     then
    0.16
     ust
    0.16
    then
    0.16
    -scrollbar
    0.16
     correspond
    0.14
    APT
    0.14
    rol
    0.14
    ix
    0.14
    untu
    0.14
    ju
    0.14
    Act Density 0.079%

    No Known Activations