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

    Neuronpedia

    INDEX
    Explanations

    comparative terms that indicate differences in quantity or quality

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.84
    ="@+
    -0.68
     @"/
    -0.65
     propOrder
    -0.64
    parsedMessage
    -0.61
    twimg
    -0.60
    ftagPool
    -0.59
    #+#
    -0.59
     kasarigan
    -0.57
    IndentedString
    -0.57
    POSITIVE LOGITS
     sinned
    0.52
    ainville
    0.51
     diagonals
    0.51
    bamb
    0.50
    jeuner
    0.49
    zwischen
    0.49
    ghijkl
    0.49
    stonia
    0.49
    consin
    0.48
     glycine
    0.48
    Act Density 0.078%

    No Known Activations