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

    Neuronpedia

    INDEX
    Explanations

    the word "low" and variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to minimal or low-quality characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andise
    -0.79
    tnc
    -0.76
     Chaser
    -0.67
    iott
    -0.67
    ADRA
    -0.66
     Ashe
    -0.65
    natureconservancy
    -0.63
     Disorder
    -0.61
    greg
    -0.61
    itutional
    -0.60
    POSITIVE LOGITS
    brow
    1.00
    ered
    0.97
    ball
    0.88
    est
    0.87
    enthal
    0.87
     hanging
    0.84
    down
    0.82
     profile
    0.80
    profile
    0.79
    enstein
    0.79
    Act Density 0.044%

    No Known Activations