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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that emphasize examples or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eric
    -0.14
     Ud
    -0.14
     Hung
    -0.14
    ë¹Į
    -0.13
    ater
    -0.13
     Shea
    -0.13
    mps
    -0.13
    rew
    -0.13
    ä¼
    -0.13
    amac
    -0.13
    POSITIVE LOGITS
    770
    0.16
    ông
    0.16
    -ÑĤо
    0.15
    ìĿ¼
    0.15
    -sex
    0.15
    eken
    0.15
    ones
    0.14
     воÑĤ
    0.14
    edList
    0.14
    pace
    0.14
    Act Density 0.052%

    No Known Activations