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

    Neuronpedia

    INDEX
    Explanations

    URLs related to academic works or research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.79
     שוליים
    -0.77
     EconPapers
    -0.72
     विश्वसनीयता
    -0.69
     Shee
    -0.68
     lenker
    -0.66
    UTERS
    -0.65
    }}
    -0.64
     abbond
    -0.64
    alyptus
    -0.61
    POSITIVE LOGITS
    dx
    2.69
     dx
    2.27
    DX
    1.78
     DX
    1.76
     Dx
    1.53
    Dx
    1.48
     dy
    1.28
    dy
    1.22
    dz
    1.04
     dz
    0.89
    Act Density 0.071%

    No Known Activations