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

    Neuronpedia

    INDEX
    Explanations

    the names of products or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various movie titles and their associated attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weaker
    -0.66
    ?).
    -0.65
    .).
    -0.62
    .)
    -0.61
    )."
    -0.60
     weak
    -0.60
     ).
    -0.59
    ).
    -0.59
     hence
    -0.59
     separately
    -0.59
    POSITIVE LOGITS
    £ı
    0.78
     (?,
    0.76
     âĵĺ
    0.74
    apeshifter
    0.66
    cellaneous
    0.65
    anguages
    0.64
    otine
    0.63
    abases
    0.63
    berra
    0.62
    abama
    0.62
    Act Density 0.496%

    No Known Activations