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

    Neuronpedia

    INDEX
    Explanations

    references to control mechanisms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unky
    -0.15
    achu
    -0.14
    iset
    -0.14
    -navbar
    -0.14
    ihn
    -0.14
    apel
    -0.14
     Buchanan
    -0.14
    ide
    -0.13
    addon
    -0.13
    bish
    -0.13
    POSITIVE LOGITS
     Blades
    0.16
     SMP
    0.14
    STYPE
    0.14
    à¤Ĥà¤ľà¤¨
    0.14
    .onreadystatechange
    0.14
    obel
    0.14
    pair
    0.13
    CMD
    0.13
    ırı
    0.13
     blades
    0.13
    Act Density 0.001%

    No Known Activations