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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, permissions, and restrictions

    oai_token-act-pair · gpt-3.5-turbo

    words indicating permission or allowance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bush
    -0.74
    entin
    -0.71
    lves
    -0.69
    fish
    -0.65
    alky
    -0.64
    tone
    -0.63
    vae
    -0.62
    blow
    -0.61
    zyme
    -0.60
    xon
    -0.59
    POSITIVE LOGITS
     access
    0.92
     exemptions
    0.81
     entry
    0.80
    ional
    0.77
     unrestricted
    0.73
     exceptions
    0.71
     downtime
    0.69
     to
    0.69
     deviations
    0.69
     unlimited
    0.67
    Act Density 0.052%

    No Known Activations