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

    Neuronpedia

    INDEX
    Explanations

    the terms and conditions statements within texts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to consent and agreements in a sign-up process

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dens
    -0.66
     afar
    -0.65
     worse
    -0.64
     hierarchy
    -0.63
     Galile
    -0.63
     vengeance
    -0.62
     divergence
    -0.62
     clos
    -0.61
     scen
    -0.61
     gal
    -0.61
    POSITIVE LOGITS
     Contribut
    0.85
    dit
    0.81
     Login
    0.80
    essage
    0.78
     consent
    0.78
     entit
    0.77
     Password
    0.75
    claimer
    0.75
     AUTH
    0.73
    oola
    0.73
    Act Density 0.132%

    No Known Activations