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

    Neuronpedia

    INDEX
    Explanations

    references to web development code and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loth
    -0.16
     Seymour
    -0.16
    antis
    -0.16
    asti
    -0.15
    atr
    -0.14
    oka
    -0.14
    arefa
    -0.14
     Tham
    -0.14
    amine
    -0.13
    Äĥr
    -0.13
    POSITIVE LOGITS
    аÑĢÑĩ
    0.15
     Truy
    0.14
    esh
    0.14
    à¥ģड
    0.14
     Shields
    0.14
    dle
    0.13
     shelter
    0.13
    Indices
    0.13
    odon
    0.13
    .ob
    0.13
    Act Density 0.008%

    No Known Activations