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

    Neuronpedia

    INDEX
    Explanations

    checkboxes or interactive elements prompting actions from users

    oai_token-act-pair · gpt-3.5-turbo

    user interface elements and actions related to forms and buttons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vironment
    -0.69
    istance
    -0.61
    past
    -0.60
    ãĥ´
    -0.59
    matter
    -0.59
    hig
    -0.59
    icion
    -0.58
    vik
    -0.57
    pread
    -0.55
    ufact
    -0.54
    POSITIVE LOGITS
    usercontent
    0.69
     Rodham
    0.66
     BELOW
    0.64
    Interstitial
    0.64
     below
    0.63
    percent
    0.56
    danger
    0.55
     Invalid
    0.55
    Subscribe
    0.55
     [|
    0.55
    Act Density 0.024%

    No Known Activations