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

    Neuronpedia

    INDEX
    Explanations

    terms related to innate or natural qualities and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ETS
    -0.17
    indr
    -0.16
     descargar
    -0.15
    彦
    -0.15
    fk
    -0.15
    acco
    -0.14
    fik
    -0.14
    orias
    -0.13
    ignant
    -0.13
    /th
    -0.13
    POSITIVE LOGITS
     natural
    0.33
     Natural
    0.32
    Natural
    0.31
     naturally
    0.28
    natural
    0.28
    /native
    0.26
     doÄŁal
    0.24
     Naturally
    0.22
    /default
    0.22
    èĩªçĦ¶
    0.22
    Act Density 0.091%

    No Known Activations