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

    Neuronpedia

    INDEX
    Explanations

    XML-related syntax and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achuset
    -0.17
    iets
    -0.16
    deaux
    -0.16
    imenti
    -0.15
    och
    -0.15
    iment
    -0.15
    erts
    -0.15
    irty
    -0.14
    roupon
    -0.14
    orsi
    -0.14
    POSITIVE LOGITS
    èĿ
    0.14
    çĩ
    0.14
    rn
    0.14
    oldur
    0.14
     Burns
    0.14
    åĨĨ
    0.14
    ë³´ê³ł
    0.14
    Ĥ
    0.14
    acf
    0.14
    bindings
    0.13
    Act Density 0.001%

    No Known Activations