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

    Neuronpedia

    INDEX
    Explanations

    percentages or proportions of a whole

    oai_token-act-pair · gpt-3.5-turbo

    statistical proportions and percentages related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ande
    -0.68
    worms
    -0.68
     overcame
    -0.65
    erity
    -0.64
     groom
    -0.62
     notwithstanding
    -0.60
    spir
    -0.60
    hur
    -0.60
    orce
    -0.60
    laws
    -0.59
    POSITIVE LOGITS
    %%
    0.80
    ibrary
    0.80
     Flavoring
    0.75
    swick
    0.75
    UF
    0.70
     territory
    0.70
     TG
    0.68
     entirety
    0.67
    OF
    0.66
    izational
    0.66
    Act Density 0.118%

    No Known Activations