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

    Neuronpedia

    INDEX
    Explanations

    adjectives followed by words related to size or degree

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" in various contexts to indicate a comparison or enhancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HCR
    -0.86
    rend
    -0.84
    asus
    -0.64
    sov
    -0.64
    RFC
    -0.63
    emp
    -0.62
    Network
    -0.62
    ~~~~~~~~
    -0.61
    Band
    -0.60
    ected
    -0.60
    POSITIVE LOGITS
    handed
    1.02
     remotely
    0.83
    handedly
    0.75
    ivari
    0.71
     though
    0.69
     MORE
    0.66
     tho
    0.65
     numbered
    0.64
    itional
    0.64
    song
    0.63
    Act Density 0.054%

    No Known Activations