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

    Neuronpedia

    INDEX
    Explanations

    articles that indicate a specific quality or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uros
    -0.17
    idir
    -0.17
    hazi
    -0.16
    ral
    -0.14
    isman
    -0.14
    moil
    -0.14
    RATION
    -0.14
    rez
    -0.13
     rather
    -0.13
    ney
    -0.13
    POSITIVE LOGITS
     necessarily
    0.25
     anymore
    0.23
     particularly
    0.21
     coincidence
    0.19
     terribly
    0.18
     isolated
    0.17
     bad
    0.17
    particularly
    0.16
    endor
    0.16
     thing
    0.16
    Act Density 0.057%

    No Known Activations