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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oleÄį
    -0.16
    iag
    -0.15
     buc
    -0.14
    ÑģÑĤи
    -0.14
    relude
    -0.14
     blat
    -0.14
    undry
    -0.14
    otty
    -0.13
     bubble
    -0.13
    ç´Ķ
    -0.13
    POSITIVE LOGITS
     exp
    0.15
    esson
    0.15
    arine
    0.14
    chner
    0.14
    amel
    0.14
    yc
    0.14
    odzi
    0.13
     Stand
    0.13
    stance
    0.13
    esp
    0.13
    Act Density 0.005%

    No Known Activations