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

    Neuronpedia

    INDEX
    Explanations

    references to a specific framework or structure within discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighton
    -0.16
    sg
    -0.16
    ãĥ¼ãĥ
    -0.16
    Ø©
    -0.15
    idd
    -0.14
    iku
    -0.14
    burgh
    -0.13
    inya
    -0.13
    ields
    -0.13
    union
    -0.13
    POSITIVE LOGITS
    strup
    0.15
    achine
    0.15
    xaa
    0.14
     hann
    0.14
    åde
    0.14
     Oswald
    0.14
    NEXT
    0.14
    adors
    0.14
    artz
    0.14
    -Encoding
    0.13
    Act Density 0.043%

    No Known Activations