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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to guidelines, specifications, or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axis
    -0.16
    TEE
    -0.16
    arrass
    -0.15
    oleon
    -0.15
    foy
    -0.15
    asse
    -0.14
    Ïĩι
    -0.14
    asil
    -0.14
    ifr
    -0.14
    erland
    -0.14
    POSITIVE LOGITS
    oad
    0.17
     especially
    0.15
     å®
    0.15
    åĪĻ
    0.15
    YZ
    0.15
    rog
    0.14
     Dun
    0.14
    HEMA
    0.14
    especially
    0.14
     Sche
    0.14
    Act Density 0.144%

    No Known Activations