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

    Neuronpedia

    INDEX
    Explanations

    references to identity or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ting
    -0.19
    atik
    -0.17
    ted
    -0.16
    веÑģÑĤ
    -0.15
    ches
    -0.15
    158
    -0.15
    uen
    -0.15
    uet
    -0.14
    uran
    -0.14
    borg
    -0.14
    POSITIVE LOGITS
     else
    0.27
    /how
    0.16
    _else
    0.16
    soever
    0.16
     ELSE
    0.16
    opi
    0.15
    erta
    0.15
    aho
    0.14
    	else
    0.14
    SSION
    0.14
    Act Density 0.019%

    No Known Activations