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

    Neuronpedia

    INDEX
    Explanations

    aspects that contribute to uniqueness or distinguishable features in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interop
    -0.16
    anza
    -0.15
    CAST
    -0.15
    imli
    -0.15
    .obtain
    -0.14
    azer
    -0.14
    ãĥ³ãĤ¿
    -0.14
    lesen
    -0.13
    ìĹ¼
    -0.13
    lish
    -0.13
    POSITIVE LOGITS
     tick
    0.23
     difference
    0.20
    tick
    0.19
     unique
    0.19
     TICK
    0.19
     Tick
    0.18
    Tick
    0.18
     Difference
    0.18
     special
    0.17
     Unique
    0.17
    Act Density 0.045%

    No Known Activations