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

    Neuronpedia

    INDEX
    Explanations

    calls to action, especially related to verifying not being a robot

    oai_token-act-pair · gpt-3.5-turbo

    requests for user verification or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abase
    -0.70
    ynt
    -0.69
    MET
    -0.69
     unaccount
    -0.68
    ilts
    -0.66
    onde
    -0.66
    Quote
    -0.66
    bara
    -0.66
    ,,,,
    -0.66
    ariat
    -0.65
    POSITIVE LOGITS
    interstitial
    0.82
     Subscribe
    0.65
    iframe
    0.64
     unlocks
    0.63
    andel
    0.62
     stimulating
    0.62
     cartoons
    0.59
     trending
    0.59
     learnt
    0.59
    î
    0.59
    Act Density 0.077%

    No Known Activations