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

    Neuronpedia

    INDEX
    Explanations

    patterns of inquiry and concern related to documentation and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     something
    -0.14
     always
    -0.13
     things
    -0.13
    _refl
    -0.13
    .idea
    -0.12
    ands
    -0.12
    iban
    -0.12
    essen
    -0.12
    оÑĢо
    -0.12
    jan
    -0.12
    POSITIVE LOGITS
    rubu
    0.13
    TRGL
    0.13
    UpInside
    0.13
    cheon
    0.13
    vap
    0.12
    _ARROW
    0.12
    ichert
    0.12
    489
    0.12
     ειÏĥ
    0.12
    @qq
    0.12
    Act Density 0.112%

    No Known Activations