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

    Neuronpedia

    INDEX
    Explanations

    questions or phrases related to quantity or value

    oai_token-act-pair · gpt-3.5-turbo

    the word "much" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.95
    Ń·
    -0.87
    idon
    -0.86
    ATURES
    -0.85
    swick
    -0.81
    ivas
    -0.80
    WAYS
    -0.80
    ands
    -0.75
    èĢ
    -0.75
    zech
    -0.75
    POSITIVE LOGITS
     damage
    0.82
     money
    0.81
     attention
    0.81
     extent
    0.80
     elapsed
    0.78
     faith
    0.78
     overlap
    0.76
     fun
    0.74
     interest
    0.74
     firepower
    0.74
    Act Density 0.026%

    No Known Activations