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

    Neuronpedia

    INDEX
    Explanations

    terms related to mechanical components or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAINT
    -0.18
    -Sah
    -0.16
    ————————————————
    -0.16
    essages
    -0.15
    usual
    -0.15
    ÑĨов
    -0.15
    ëĭ¤
    -0.15
    cks
    -0.14
    irtual
    -0.14
     usual
    -0.14
    POSITIVE LOGITS
    s
    0.63
    y
    0.44
    mente
    0.34
    ity
    0.30
    sand
    0.26
    ness
    0.26
    sak
    0.26
    soup
    0.25
    sense
    0.24
    Ùĩ
    0.23
    Act Density 0.043%

    No Known Activations