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

    Neuronpedia

    INDEX
    Explanations

    concepts related to specific products, systems, and their impact in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     embod
    -0.17
     would
    -0.16
     may
    -0.15
    quete
    -0.15
     might
    -0.15
    ALSE
    -0.15
    Spoiler
    -0.15
    Äįel
    -0.14
    _should
    -0.14
    OULD
    -0.14
    POSITIVE LOGITS
     supposed
    0.28
     worth
    0.25
     gonna
    0.24
     going
    0.20
     suppose
    0.19
     afraid
    0.19
     a
    0.19
     considered
    0.19
     really
    0.18
     able
    0.18
    Act Density 0.098%

    No Known Activations