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

    Neuronpedia

    INDEX
    Explanations

    descriptions of architectural or design features in environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mine
    -0.16
     Beginner
    -0.15
    à¸ķร
    -0.15
    crow
    -0.14
     relativ
    -0.13
    Bounding
    -0.13
     marg
    -0.13
     rat
    -0.13
    ç
    -0.13
     Alman
    -0.13
    POSITIVE LOGITS
     suspended
    0.19
    uspended
    0.19
    conc
    0.17
     steel
    0.16
    Hang
    0.15
     transparency
    0.15
    igram
    0.15
    ELEMENT
    0.15
     dna
    0.14
     conc
    0.14
    Act Density 0.142%

    No Known Activations