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

    Neuronpedia

    INDEX
    Explanations

    references to different topics within a discussion or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ers
    -0.20
    outs
    -0.18
    out
    -0.16
    ora
    -0.16
    ude
    -0.16
    iggers
    -0.15
    ering
    -0.15
    orta
    -0.15
    aby
    -0.15
    iciencies
    -0.15
    POSITIVE LOGITS
    starter
    0.25
    æĿIJ
    0.19
    (topic
    0.18
    perature
    0.18
     areas
    0.17
     covered
    0.17
     ÄijÃŃch
    0.16
    areas
    0.16
    steller
    0.16
    ALLY
    0.15
    Act Density 0.012%

    No Known Activations