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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance or significance in a context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    CPtr
    -0.71
    béco
    -0.67
    COUVER
    -0.67
    Przypisy
    -0.64
    PhysRevLett
    -0.64
    gameserver
    -0.63
    ControllerTest
    -0.62
     <=",
    -0.62
     invokingState
    -0.60
    posób
    -0.60
    POSITIVE LOGITS
    ktop
    0.60
    upsi
    0.54
     myriad
    0.52
     altera
    0.51
    ArrowToggle
    0.49
     numerous
    0.48
     Prophecy
    0.48
    Nazionale
    0.48
     roda
    0.48
    numer
    0.47
    Act Density 0.048%

    No Known Activations