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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "or" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esk
    -0.17
    urve
    -0.16
    empo
    -0.16
    太éĥİ
    -0.15
    onian
    -0.15
    ваÑı
    -0.14
    icago
    -0.14
    indle
    -0.14
    YW
    -0.14
    URES
    -0.14
    POSITIVE LOGITS
    phans
    0.30
    /or
    0.30
    ifice
    0.25
     indeed
    0.24
    lando
    0.23
    acular
    0.23
    许
    0.23
     even
    0.21
     else
    0.21
    acles
    0.21
    Act Density 0.269%

    No Known Activations