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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting misleading or suppressed information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parentNode
    -0.15
    asing
    -0.15
    rina
    -0.15
    cÃŃ
    -0.14
    ¼åIJĪ
    -0.14
    æ§
    -0.14
    aben
    -0.14
    Ŀå§ĭ
    -0.13
    ello
    -0.13
    WebSocket
    -0.13
    POSITIVE LOGITS
    udev
    0.18
    _IGNORE
    0.16
    terra
    0.14
    essor
    0.14
    .experimental
    0.14
     hides
    0.14
    berger
    0.14
     Lim
    0.14
    raf
    0.14
    ICS
    0.14
    Act Density 0.174%

    No Known Activations