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

    Neuronpedia

    INDEX
    Explanations

    elements of structured or academic writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    émon
    -0.16
    adors
    -0.16
    ander
    -0.15
    ambah
    -0.15
    riott
    -0.14
    μον
    -0.14
    esson
    -0.14
    asje
    -0.14
    dek
    -0.14
    edith
    -0.14
    POSITIVE LOGITS
     pur
    0.23
     fel
    0.21
    pur
    0.21
     tort
    0.20
     magna
    0.18
     Pur
    0.18
     met
    0.18
     tell
    0.18
     eros
    0.18
    fel
    0.17
    Act Density 0.003%

    No Known Activations