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

    Neuronpedia

    INDEX
    Explanations

    references to symbolic concepts and representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.17
    935
    -0.16
    rott
    -0.15
    ÑĢиг
    -0.15
    rens
    -0.15
    ully
    -0.14
    ì¸
    -0.14
    ughter
    -0.14
    atra
    -0.14
    ellig
    -0.14
    POSITIVE LOGITS
    chai
    0.15
    oenix
    0.15
    minent
    0.15
    urat
    0.15
    HideInInspector
    0.15
    mith
    0.15
    phants
    0.14
     Kee
    0.14
    dden
    0.14
     Ñģобой
    0.14
    Act Density 0.021%

    No Known Activations