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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or labels that categorize information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Official
    -0.17
     official
    -0.17
    ä»ĭ
    -0.15
     couch
    -0.15
    aid
    -0.15
    aya
    -0.14
     advance
    -0.14
     bleach
    -0.14
     contributions
    -0.14
     str
    -0.13
    POSITIVE LOGITS
    ARED
    0.18
    ARE
    0.17
    YLON
    0.16
    radient
    0.15
    оÑĢаз
    0.15
    rows
    0.15
    Script
    0.15
    ови
    0.15
    dup
    0.14
    ares
    0.14
    Act Density 0.045%

    No Known Activations