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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases indicating possibilities and potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    deen
    -0.18
    ordum
    -0.17
    oldt
    -0.15
    intree
    -0.14
    ácil
    -0.14
    imeo
    -0.14
    OTO
    -0.14
    ynamodb
    -0.14
    iseum
    -0.14
     Addr
    -0.14
    POSITIVE LOGITS
     Scha
    0.17
    alsa
    0.16
    ador
    0.14
     beden
    0.14
    æĸĩ
    0.14
     rip
    0.14
     ora
    0.14
     Sommer
    0.14
     Schwar
    0.14
    они
    0.14
    Act Density 0.163%

    No Known Activations