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

    Neuronpedia

    INDEX
    Explanations

    percentages and their related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ington
    -0.15
    lisi
    -0.15
    åľ¨çº¿
    -0.14
    ider
    -0.14
     Blanch
    -0.14
     proof
    -0.14
    enburg
    -0.13
     Proof
    -0.13
    ansa
    -0.13
    arendra
    -0.13
    POSITIVE LOGITS
     Nhĩ
    0.15
    ween
    0.15
     dw
    0.15
    imilar
    0.14
     Rew
    0.14
    ufs
    0.14
    irie
    0.14
    Rew
    0.14
    adel
    0.14
    pter
    0.13
    Act Density 0.054%

    No Known Activations