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

    Neuronpedia

    INDEX
    Explanations

    phrases related to safety and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    217
    -0.15
    CEE
    -0.15
    миÑĢ
    -0.15
    ãĥ£
    -0.15
    anna
    -0.14
     Specialist
    -0.14
    igli
    -0.14
    adin
    -0.14
     Founder
    -0.14
     Fro
    -0.13
    POSITIVE LOGITS
    á»Ļc
    0.15
     eject
    0.14
    /goto
    0.14
    åŃĺäºİ
    0.13
    obra
    0.13
     hors
    0.13
    atan
    0.13
    ÑĢÑĥкÑĤ
    0.13
     Kum
    0.13
    GetObject
    0.13
    Act Density 0.539%

    No Known Activations