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

    Neuronpedia

    INDEX
    Explanations

    keywords related to gates and access control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGraphics
    -0.80
    Wallis
    -0.79
     Woodbridge
    -0.77
     useStyles
    -0.76
    Roberts
    -0.74
    jabi
    -0.74
    Obr
    -0.73
     Cornish
    -0.73
    ècie
    -0.71
     Kras
    -0.71
    POSITIVE LOGITS
     gates
    1.56
     gate
    1.56
     Gate
    1.50
     Gates
    1.41
    Gate
    1.37
    Gates
    1.23
     GATE
    1.19
    gates
    1.14
    gate
    1.05
     gated
    1.03
    Act Density 0.080%

    No Known Activations