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

    Neuronpedia

    INDEX
    Explanations

    references to different types of media like images and media players

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cker
    -0.78
    gling
    -0.70
    ŃĶ
    -0.69
    ãĤ¡
    -0.68
    vasive
    -0.67
    bats
    -0.67
    abouts
    -0.66
    ģ«
    -0.65
     damn
    -0.63
     Rasmussen
    -0.62
    POSITIVE LOGITS
    eval
    1.37
     outlets
    1.03
    wiki
    0.91
     literacy
    0.89
     mog
    0.81
     outlet
    0.81
     mogul
    0.78
     conglomer
    0.74
     consolidation
    0.72
     VIDEOS
    0.72
    Act Density 0.032%

    No Known Activations