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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software or computing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and digital media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.55
     corpor
    -0.55
     major
    -0.53
     blister
    -0.53
     massive
    -0.51
     kernels
    -0.51
     deadly
    -0.50
     gru
    -0.50
     arsen
    -0.49
     overcrowd
    -0.49
    POSITIVE LOGITS
    tenance
    1.18
    terday
    0.88
    theless
    0.85
    iculty
    0.80
    mosp
    0.72
    ruction
    0.72
    iversary
    0.72
    acters
    0.68
    uration
    0.67
    veyard
    0.66
    Act Density 0.597%

    No Known Activations