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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements and specific function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dims
    -0.15
    875
    -0.15
    ully
    -0.15
     cliff
    -0.14
     scatter
    -0.14
    anela
    -0.14
    bach
    -0.14
    ithub
    -0.14
    DMIN
    -0.13
    jev
    -0.13
    POSITIVE LOGITS
    irc
    0.16
     lần
    0.15
    ellen
    0.14
    fé
    0.14
    dera
    0.14
    ogi
    0.14
    ezier
    0.14
    vice
    0.14
    icho
    0.14
    scar
    0.14
    Act Density 0.001%

    No Known Activations