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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating error messages in email subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating issues with email subscription validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atri
    -0.65
    pled
    -0.64
    naire
    -0.63
    ouses
    -0.59
     vis
    -0.58
    rams
    -0.58
    hid
    -0.58
    audi
    -0.57
     normalized
    -0.57
     endeavor
    -0.57
    POSITIVE LOGITS
     defences
    0.76
     Thumbnails
    0.75
     Email
    0.74
    agher
    0.73
     Zealand
    0.68
     Archive
    0.68
    BBC
    0.66
    Skip
    0.65
    Filter
    0.63
     Hades
    0.62
    Act Density 0.012%

    No Known Activations