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

    Neuronpedia

    INDEX
    Explanations

    key terms related to research studies and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.94
    tvguidetime
    -0.91
     الدولى
    -0.86
    GEBURTSDATUM
    -0.80
    NUMX
    -0.75
    новништво
    -0.75
     AssemblyVersion
    -0.74
    ImageContext
    -0.72
    ConstraintMaker
    -0.71
    Portail
    -0.71
    POSITIVE LOGITS
     is
    0.62
    is
    0.48
    p
    0.47
    lo
    0.46
    y
    0.46
    tes
    0.45
     may
    0.45
    uris
    0.44
     ur
    0.44
     also
    0.44
    Act Density 0.525%

    No Known Activations