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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values associated with time or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uter
    -0.17
    wig
    -0.15
    editary
    -0.15
    uster
    -0.15
    ornings
    -0.15
    atter
    -0.14
    extr
    -0.14
    urg
    -0.14
    inalg
    -0.14
    atures
    -0.14
    POSITIVE LOGITS
     Sigma
    0.24
    MSN
    0.21
    ï¸ı
    0.20
     Flags
    0.19
    Sigma
    0.18
    ooth
    0.18
     sigma
    0.18
     different
    0.18
    am
    0.17
     SIG
    0.17
    Act Density 0.148%

    No Known Activations