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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.16
     mell
    -0.14
    outer
    -0.14
    _outer
    -0.14
     outer
    -0.14
     exact
    -0.14
    bett
    -0.14
    icap
    -0.13
     loc
    -0.13
    ļ
    -0.13
    POSITIVE LOGITS
    ture
    0.18
    ovna
    0.17
     herself
    0.17
    lify
    0.17
    stery
    0.16
     ÑģÑĤала
    0.15
     Pregn
    0.15
    .Encode
    0.15
    oreach
    0.14
    spar
    0.14
    Act Density 0.222%

    No Known Activations