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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the use or interpretation of expressions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "expression" and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bullets
    -0.85
     Shades
    -0.73
     Brewers
    -0.70
    elcome
    -0.69
    END
    -0.68
    ether
    -0.68
     Peb
    -0.66
     Mariners
    -0.65
    Ń·
    -0.65
     Skydragon
    -0.65
    POSITIVE LOGITS
    terday
    0.92
    ist
    0.82
    uated
    0.81
     expression
    0.78
    ation
    0.74
     expressions
    0.72
    ivity
    0.72
     Expression
    0.71
     guiActiveUn
    0.70
    orious
    0.70
    Act Density 0.027%

    No Known Activations