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

    Neuronpedia

    INDEX
    Explanations

    strong adjectives and descriptors indicating significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Block
    -0.16
    auge
    -0.15
    vro
    -0.15
    anja
    -0.15
    ä¸Ģç§į
    -0.15
    zcze
    -0.14
    ernal
    -0.14
    -ajax
    -0.14
    imson
    -0.14
     stitch
    -0.14
    POSITIVE LOGITS
     Cobb
    0.16
    FOUNDATION
    0.15
    ooter
    0.15
    dal
    0.14
    asurer
    0.14
    ëł´
    0.14
    DOB
    0.14
     Takım
    0.14
    lingen
    0.14
     excess
    0.14
    Act Density 0.014%

    No Known Activations