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

    Neuronpedia

    INDEX
    Explanations

    negation or concepts of unfairness and unreasonableness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actively
    -0.16
    isible
    -0.15
    orgot
    -0.14
    ensitive
    -0.14
    singular
    -0.14
    å²³
    -0.14
    usch
    -0.14
    áp
    -0.14
    disposed
    -0.13
    assume
    -0.13
    POSITIVE LOGITS
    scr
    0.21
     sustainable
    0.19
    wise
    0.18
    pal
    0.17
    mask
    0.16
    just
    0.16
     scr
    0.16
     Barg
    0.16
    brid
    0.16
    fruit
    0.16
    Act Density 0.025%

    No Known Activations