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

    Neuronpedia

    INDEX
    Explanations

    words related to evaluation and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungan
    -0.17
    icho
    -0.16
    stk
    -0.15
    Wunused
    -0.15
    ÅĤaw
    -0.15
    ãĤ¯
    -0.15
    ÙĪرÙĩ
    -0.15
    Formatting
    -0.15
    838
    -0.15
    éı
    -0.15
    POSITIVE LOGITS
    orpion
    0.14
     Ol
    0.14
     aks
    0.14
    IGGER
    0.14
    enes
    0.14
     Tong
    0.14
     amber
    0.13
     Priority
    0.13
     Snowden
    0.13
     rarity
    0.13
    Act Density 0.010%

    No Known Activations