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

    Neuronpedia

    INDEX
    Explanations

    references to safety concerns and product evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Regards
    -0.18
    olla
    -0.16
    ýt
    -0.15
     Lyons
    -0.15
    avis
    -0.14
    erset
    -0.14
    halt
    -0.14
    MOTE
    -0.14
    isoft
    -0.14
    _metric
    -0.14
    POSITIVE LOGITS
    tha
    0.17
     det
    0.14
    zens
    0.14
     ADVISED
    0.14
     spear
    0.14
    ãģĮãģĦ
    0.13
    ÙĬÙĬÙĨ
    0.13
    ENDED
    0.13
    Ķ
    0.13
    ¯
    0.13
    Act Density 0.012%

    No Known Activations