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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to user interface elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ijn
    -0.17
    /english
    -0.16
    nown
    -0.14
    IDENT
    -0.14
    ihn
    -0.14
     è©ķ
    -0.14
    íĢ
    -0.14
    èīĩ
    -0.13
    ÑĤаб
    -0.13
    serter
    -0.13
    POSITIVE LOGITS
     contents
    0.20
     Äijá»Ŀi
    0.17
    contents
    0.16
     containing
    0.16
    ahlen
    0.15
    ibbon
    0.14
     definitions
    0.14
    ened
    0.14
    ertz
    0.14
     definition
    0.14
    Act Density 0.051%

    No Known Activations