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

    Neuronpedia

    INDEX
    Explanations

    words related to laboratory settings and equipment

    oai_token-act-pair · gpt-3.5-turbo

    references to laboratory settings or lab-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nerv
    -0.65
     Supporters
    -0.62
     church
    -0.60
    lihood
    -0.60
     Voters
    -0.58
     Masquerade
    -0.57
    abouts
    -0.57
     impunity
    -0.56
     Immunity
    -0.55
    theless
    -0.55
    POSITIVE LOGITS
    rador
    1.58
    yrinth
    1.48
    elling
    1.28
    orer
    1.22
    elled
    1.17
    orers
    1.15
    eled
    1.01
    orously
    1.01
    ours
    1.00
    orde
    0.94
    Act Density 0.047%

    No Known Activations