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

    Neuronpedia

    INDEX
    Explanations

    subscriptions or opt-in instructions in emails

    oai_token-act-pair · gpt-3.5-turbo

    references to news sources and their content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.62
    auga
    -0.61
    naire
    -0.57
    itled
    -0.57
     footsteps
    -0.55
     pie
    -0.53
     precedence
    -0.53
     precedent
    -0.52
     screening
    -0.52
     opacity
    -0.52
    POSITIVE LOGITS
     POLITICO
    0.78
    ivably
    0.72
    bleacher
    0.69
     subscribing
    0.63
    independent
    0.62
     Contra
    0.62
    Dispatch
    0.61
    azz
    0.60
     Cycling
    0.59
     Buzz
    0.59
    Act Density 0.025%

    No Known Activations