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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "explicit"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "explicit" or related concepts indicating clarity and directness in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tycoon
    -0.85
    nesota
    -0.81
    STON
    -0.80
    «ĺ
    -0.77
    Score
    -0.75
    Dur
    -0.74
    Squ
    -0.73
    games
    -0.69
     Stanton
    -0.69
    Kenn
    -0.68
    POSITIVE LOGITS
     guiActiveUn
    0.84
     explicit
    0.79
     explicitly
    0.78
     textual
    0.76
     deline
    0.73
    ities
    0.72
     coded
    0.70
     hint
    0.69
    bidden
    0.69
     repud
    0.67
    Act Density 0.032%

    No Known Activations