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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation, particularly approximations denoted by widehat symbols

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    marle
    -0.79
     Mard
    -0.75
    BeforeEach
    -0.74
     Dole
    -0.73
    apunov
    -0.73
     Hartley
    -0.72
     McIl
    -0.72
    antMatchers
    -0.71
    mq
    -0.71
    LayoutConstraint
    -0.71
    POSITIVE LOGITS
    widehat
    1.82
     Truss
    0.83
     Tamar
    0.82
    Jacobs
    0.82
    setTransform
    0.78
     RTP
    0.77
     Jacobs
    0.77
     tass
    0.76
    Tamar
    0.75
    Extinguishing
    0.74
    Act Density 0.001%

    No Known Activations