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

    Neuronpedia

    INDEX
    Explanations

    significant phrases related to processes or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alis
    -0.19
    ox
    -0.16
    orr
    -0.16
    vor
    -0.16
    vs
    -0.16
    lc
    -0.16
    afil
    -0.15
    ass
    -0.15
    owa
    -0.14
    sv
    -0.14
    POSITIVE LOGITS
     ones
    0.20
    ildo
    0.15
    unge
    0.15
    alette
    0.14
    oogle
    0.14
     напÑĢимеÑĢ
    0.14
    unta
    0.14
    inand
    0.14
    á»įng
    0.13
    nÃŃky
    0.13
    Act Density 0.241%

    No Known Activations