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

    Neuronpedia

    INDEX
    Explanations

    color-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to colors and various social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Legend
    -0.64
    1001
    -0.63
    Operation
    -0.58
    Nav
    -0.56
    ª
    -0.55
    FY
    -0.54
    TOP
    -0.54
    ãĥīãĥ©
    -0.54
    Reloaded
    -0.53
    äºĶ
    -0.53
    POSITIVE LOGITS
     alike
    1.65
     respectively
    1.63
     etc
    1.00
     and
    0.81
     interchange
    0.80
     together
    0.77
     weren
    0.75
     blah
    0.75
     versa
    0.74
     AND
    0.70
    Act Density 0.351%

    No Known Activations