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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permission or prohibition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to permissions and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Balanced
    -0.78
     doomed
    -0.68
     Opportun
    -0.67
    finder
    -0.66
     Needs
    -0.65
    forcing
    -0.64
    nces
    -0.64
     Ens
    -0.64
    matched
    -0.63
    gradient
    -0.62
    POSITIVE LOGITS
     participate
    1.33
     enter
    1.21
     partake
    1.19
     roam
    1.18
     speak
    1.18
     operate
    1.13
     attend
    1.10
     possess
    1.09
     marry
    1.06
     practise
    1.04
    Act Density 0.147%

    No Known Activations