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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zeug
    -0.16
    zag
    -0.16
    gest
    -0.15
    undi
    -0.15
    elic
    -0.15
    ugh
    -0.15
    hong
    -0.15
    ellig
    -0.14
    aris
    -0.14
    uggage
    -0.14
    POSITIVE LOGITS
     limited
    0.52
    limited
    0.43
     Limited
    0.40
     LIMITED
    0.38
    Limited
    0.38
    LIMIT
    0.30
     restricted
    0.29
     limit
    0.28
     limitation
    0.28
     exclusive
    0.28
    Act Density 0.006%

    No Known Activations