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

    Neuronpedia

    INDEX
    Explanations

    references to previews or sneak peeks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "preview."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fighting
    -0.83
    abases
    -0.77
    annis
    -0.75
    die
    -0.75
    BuyableInstoreAndOnline
    -0.74
    lethal
    -0.73
    isma
    -0.73
    llular
    -0.71
    profits
    -0.71
    ternity
    -0.71
    POSITIVE LOGITS
     pane
    0.86
    éĹĺ
    0.83
     preview
    0.81
    spective
    0.78
     Preview
    0.76
     reel
    0.74
    Kings
    0.74
     Mock
    0.70
     previews
    0.69
    essim
    0.69
    Act Density 0.014%

    No Known Activations