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

    Neuronpedia

    INDEX
    Explanations

    words associated with seeking help, guidance, or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.16
    430
    -0.14
     Animalia
    -0.14
    394
    -0.14
    555
    -0.14
    857
    -0.13
    viso
    -0.13
     Ulus
    -0.13
    ickers
    -0.13
    imedia
    -0.13
    POSITIVE LOGITS
    \CMS
    0.17
    .nano
    0.16
     Kurd
    0.15
    Injected
    0.14
    istrovstvÃŃ
    0.14
    .fromFunction
    0.14
    ahun
    0.14
    OLA
    0.13
    arov
    0.13
    Feat
    0.13
    Act Density 0.258%

    No Known Activations