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

    Neuronpedia

    INDEX
    Explanations

    structured discussions and analyses of various topics or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    天天
    -0.15
    Interop
    -0.14
    ixmap
    -0.14
    -Sah
    -0.14
    enÃŃ
    -0.13
    jections
    -0.13
    ialect
    -0.13
    견
    -0.13
     åĵ
    -0.12
    inite
    -0.12
    POSITIVE LOGITS
     how
    0.29
    how
    0.26
     ways
    0.21
     briefly
    0.20
     cómo
    0.20
     why
    0.20
    å¦Ĥä½ķ
    0.18
     shortly
    0.17
    owitz
    0.17
     hoe
    0.16
    Act Density 0.131%

    No Known Activations