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

    Neuronpedia

    INDEX
    Explanations

    references to detection and measurements in studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.15
    ias
    -0.14
     belts
    -0.14
    hev
    -0.14
     sendo
    -0.14
    hey
    -0.14
    pray
    -0.13
     cock
    -0.13
    ologi
    -0.13
    omi
    -0.13
    POSITIVE LOGITS
    enticator
    0.16
    strup
    0.15
    .createClass
    0.15
    utsche
    0.15
    elon
    0.14
    iler
    0.14
    oret
    0.14
    echn
    0.14
     reuseIdentifier
    0.14
    zure
    0.14
    Act Density 0.110%

    No Known Activations