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

    Neuronpedia

    INDEX
    Explanations

    calls to action to sign up for various services and newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for services or newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensen
    -0.81
    mith
    -0.79
    loo
    -0.77
    ult
    -0.75
    gypt
    -0.71
    illin
    -0.68
    clair
    -0.68
    matter
    -0.68
    ens
    -0.67
    lein
    -0.67
    POSITIVE LOGITS
     captcha
    0.81
     membership
    0.79
     TRI
    0.72
     renewal
    0.71
    ypes
    0.70
     participation
    0.70
    abee
    0.69
     grabs
    0.69
     parole
    0.67
     tyr
    0.66
    Act Density 0.042%

    No Known Activations