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

    Neuronpedia

    INDEX
    Explanations

    specific keywords and terms related to organizational structures and categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bruar
    -0.15
     Hlav
    -0.15
    .eng
    -0.15
    alborg
    -0.15
    RefCount
    -0.15
    okud
    -0.14
    irl
    -0.14
    terra
    -0.14
    vik
    -0.14
    tero
    -0.14
    POSITIVE LOGITS
     Staples
    0.15
     pret
    0.14
    esser
    0.14
     Chall
    0.14
     trot
    0.14
    rie
    0.14
    êµŃ
    0.14
     Arist
    0.13
    æŃ
    0.13
    zig
    0.13
    Act Density 0.024%

    No Known Activations