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

    Neuronpedia

    INDEX
    Explanations

    the word "decent"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "decent" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hop
    -0.84
    sten
    -0.83
    CHAT
    -0.71
    tein
    -0.71
    yang
    -0.71
    psy
    -0.68
    udic
    -0.65
    è¦ļéĨĴ
    -0.65
    burst
    -0.64
    eds
    -0.63
    POSITIVE LOGITS
     enough
    1.02
     decent
    1.00
    enough
    0.99
     sized
    0.98
    etheless
    0.82
     Enough
    0.81
    GoldMagikarp
    0.81
     chunk
    0.79
    tarian
    0.77
     quality
    0.75
    Act Density 0.010%

    No Known Activations