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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code snippets related to function definitions and conditional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linkplain
    -0.17
    wers
    -0.16
    swire
    -0.16
    ambre
    -0.16
    apsulation
    -0.16
    änn
    -0.16
    Caps
    -0.15
    IMO
    -0.15
    ANCED
    -0.15
    .vn
    -0.15
    POSITIVE LOGITS
    oran
    0.17
    ief
    0.15
    if
    0.15
    avia
    0.15
    dy
    0.14
    ohon
    0.14
    orf
    0.14
     Crossing
    0.14
    iphy
    0.13
    f
    0.13
    Act Density 0.171%

    No Known Activations