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

    Neuronpedia

    INDEX
    Explanations

    specific articles or stories, possibly from news outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to news articles and stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibles
    -0.64
     joystick
    -0.63
    imus
    -0.62
     practise
    -0.62
     natives
    -0.61
    emonic
    -0.60
     dues
    -0.59
     fulfil
    -0.59
    arers
    -0.57
    ucer
    -0.56
    POSITIVE LOGITS
     headlined
    1.40
     titled
    1.11
     alleging
    1.07
     reporting
    1.05
     headline
    0.98
     detailing
    0.97
     published
    0.97
    article
    0.96
     article
    0.95
     exposing
    0.93
    Act Density 0.131%

    No Known Activations