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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of complexity and connection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    statt
    -0.17
    ephy
    -0.15
    å¢
    -0.15
    panse
    -0.15
    rega
    -0.14
    اÙħØ©
    -0.14
    aldo
    -0.14
    _IW
    -0.14
    .Companion
    -0.14
    WXYZ
    -0.14
    POSITIVE LOGITS
    ocaly
    0.15
     Fatal
    0.14
    ormap
    0.14
    dir
    0.14
     ultimately
    0.14
     Portal
    0.13
     NDEBUG
    0.13
    gre
    0.13
    andin
    0.13
     again
    0.13
    Act Density 0.005%

    No Known Activations