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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases relating to size, level, or status among various entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "The more ..., the more ..." construction

    np_acts-logits-general · gemini-2.0-flash

    the more... the more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okat
    -0.51
     betweenstory
    -0.49
     h
    -0.44
    )}+\
    -0.43
     del
    -0.43
    )':
    -0.42
    ̉
    -0.42
    olari
    -0.41
     melainkan
    -0.41
     m
    -0.40
    POSITIVE LOGITS
     desto
    1.18
     càng
    1.15
     semakin
    1.13
     cuanto
    0.98
     Чем
    0.96
    越是
    0.93
    越
    0.88
     čím
    0.86
    Чем
    0.84
     Quanto
    0.83
    Act Density 0.185%

    No Known Activations