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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a restriction or scarcity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neau
    -0.16
    kar
    -0.15
    _limits
    -0.15
    ically
    -0.15
    ker
    -0.15
    herit
    -0.15
    eparator
    -0.15
    wich
    -0.14
    intree
    -0.14
    eger
    -0.14
    POSITIVE LOGITS
     Liability
    0.24
    rophe
    0.23
    lessly
    0.22
     liability
    0.21
     edition
    0.21
     scope
    0.21
     LIABILITY
    0.20
    iations
    0.19
    Edition
    0.18
     Edition
    0.18
    Act Density 0.057%

    No Known Activations