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

    Neuronpedia

    INDEX
    Explanations

    references to correctness and correction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.17
    ãĥŃãĥ¼
    -0.16
    /desktop
    -0.16
    okoj
    -0.15
    istics
    -0.15
    ạp
    -0.15
    aggi
    -0.14
    ized
    -0.14
    loub
    -0.14
    lings
    -0.14
    POSITIVE LOGITS
    ives
    0.28
    ive
    0.27
    s
    0.21
    ively
    0.20
    iveness
    0.20
    IVES
    0.20
    ible
    0.20
    itude
    0.19
    IVE
    0.19
    eted
    0.19
    Act Density 0.023%

    No Known Activations