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

    Neuronpedia

    INDEX
    Explanations

    mentions of government-related agencies and security initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢаб
    -0.16
     ama
    -0.15
    ç¿
    -0.14
    天åłĤ
    -0.14
     FLOAT
    -0.14
     Timing
    -0.14
    ju
    -0.14
     Float
    -0.14
     gravity
    -0.14
    atro
    -0.14
    POSITIVE LOGITS
     Oak
    0.39
     DOE
    0.37
    Oak
    0.33
     Liver
    0.30
    DO
    0.30
     Arg
    0.26
     Lawrence
    0.26
    Liver
    0.25
     oak
    0.25
     Brook
    0.24
    Act Density 0.042%

    No Known Activations