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

    Neuronpedia

    INDEX
    Explanations

    appearances or mentions of specific items or characteristics in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appear" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shaw
    -0.87
    rient
    -0.80
    ricular
    -0.78
    dp
    -0.71
    cise
    -0.70
    ça
    -0.69
    sted
    -0.68
    pping
    -0.68
    ritical
    -0.67
    brace
    -0.67
    POSITIVE LOGITS
    DragonMagazine
    0.91
    Magikarp
    0.83
    Pause
    0.75
     Minion
    0.73
    Crash
    0.70
     contradictions
    0.70
    iary
    0.69
    MG
    0.67
    Coin
    0.67
    lihood
    0.66
    Act Density 0.040%

    No Known Activations