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

    Neuronpedia

    INDEX
    Explanations

    words related to influence and impact

    oai_token-act-pair · gpt-3.5-turbo

    terms related to popularity, influence, and success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nice
    -0.73
     Cull
    -0.68
    anton
    -0.64
    cot
    -0.64
     Schne
    -0.63
     Manufact
    -0.61
    odon
    -0.60
    olulu
    -0.60
    hea
    -0.60
     Coat
    -0.59
    POSITIVE LOGITS
     depends
    1.28
     extends
    1.19
     depended
    1.14
     hinges
    1.11
     revolves
    1.11
     differs
    1.11
     varies
    1.10
     coincides
    1.09
     derives
    1.07
     dwind
    1.06
    Act Density 0.204%

    No Known Activations