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

    Neuronpedia

    INDEX
    Explanations

    text related to player interactions within a game

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to game mechanics and player interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.60
    hawks
    -0.57
    lance
    -0.56
     prosecutions
    -0.53
     understatement
    -0.53
    rists
    -0.53
    Ted
    -0.52
     Journalism
    -0.51
     Cosponsors
    -0.51
    pdf
    -0.51
    POSITIVE LOGITS
     predetermined
    0.76
     desired
    0.71
    )).
    0.68
     specified
    0.65
     adjacent
    0.59
     nearest
    0.58
     milliseconds
    0.55
     securely
    0.54
     configured
    0.54
     tile
    0.54
    Act Density 1.613%

    No Known Activations