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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "active" and its derivatives, indicating participation and engagement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occo
    -0.15
    achs
    -0.15
    ahan
    -0.15
    verbatim
    -0.14
    ers
    -0.14
    nga
    -0.14
    osaic
    -0.14
    phere
    -0.14
     __("
    -0.14
    arian
    -0.14
    POSITIVE LOGITS
    /pass
    0.18
    -active
    0.18
    .Active
    0.16
    yonel
    0.16
    (active
    0.15
    _inactive
    0.15
    748
    0.15
    /react
    0.15
    OURSE
    0.15
    NES
    0.14
    Act Density 0.036%

    No Known Activations