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

    Neuronpedia

    INDEX
    Explanations

    comparative expressions involving degrees, such as "more of" something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a continuation or addition of thoughts, often relating to comparisons or elaborations on a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Traff
    -0.74
     Peaks
    -0.68
    ALSE
    -0.66
    ADS
    -0.66
     Bulgar
    -0.65
     Gemini
    -0.65
     Ascension
    -0.65
    ij士
    -0.65
    EStream
    -0.64
    %);
    -0.63
    POSITIVE LOGITS
     than
    1.07
    rily
    0.84
    than
    0.81
    angled
    0.78
    ente
    0.76
    itably
    0.76
    ented
    0.75
    worldly
    0.75
    risome
    0.73
    leans
    0.73
    Act Density 0.107%

    No Known Activations