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

    Neuronpedia

    INDEX
    Explanations

    phrases indicative of social or political critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erland
    -0.15
    asher
    -0.15
    \Carbon
    -0.14
    plib
    -0.14
    ucz
    -0.14
    lopedia
    -0.14
    ummer
    -0.14
    ENSE
    -0.14
    asmus
    -0.14
    ownik
    -0.14
    POSITIVE LOGITS
    affle
    0.14
    éłĨ
    0.14
    pler
    0.14
     btnCancel
    0.14
    ĶåĽŀ
    0.14
    sk
    0.14
    Vis
    0.14
    olle
    0.13
    467
    0.13
    æºĸ
    0.13
    Act Density 0.355%

    No Known Activations