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

    Neuronpedia

    INDEX
    Explanations

    instances of discovery or realization in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    forme
    -0.18
    ylko
    -0.16
    ách
    -0.15
    eyin
    -0.14
    rique
    -0.14
    rech
    -0.14
    าà¸ŀ
    -0.14
     обÑĢазом
    -0.14
    fts
    -0.14
    uju
    -0.14
    POSITIVE LOGITS
     Bing
    0.16
     Atlantic
    0.16
    OC
    0.15
     Lange
    0.15
    ick
    0.15
    ãĥ³ãĤ°ãĥ«
    0.14
     sham
    0.14
    ħ
    0.14
    Keyboard
    0.14
    Atlantic
    0.14
    Act Density 0.404%

    No Known Activations