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

    Neuronpedia

    INDEX
    Explanations

    news headlines or captions embedded in medias

    oai_token-act-pair · gpt-3.5-turbo

    references to media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Phi
    -0.65
     Kappa
    -0.61
     hindsight
    -0.57
    bats
    -0.57
     Afgh
    -0.57
    clus
    -0.57
     Plum
    -0.56
    stood
    -0.55
    manship
    -0.55
     SOM
    -0.55
    POSITIVE LOGITS
     caption
    1.11
     playback
    0.88
     copyright
    0.62
    Getty
    0.62
    atalie
    0.62
    ecast
    0.61
     codec
    0.61
    Node
    0.61
    scripts
    0.60
    "]=>
    0.59
    Act Density 0.004%

    No Known Activations