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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to different types of strains

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of strains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.98
    fman
    -0.92
    vernment
    -0.85
    naissance
    -0.84
    inez
    -0.83
    emouth
    -0.83
    merce
    -0.83
    issance
    -0.82
    tarians
    -0.80
    vertisements
    -0.80
    POSITIVE LOGITS
     strains
    1.09
     strain
    1.07
     spores
    0.79
     bred
    0.73
    weed
    0.67
    igo
    0.64
     crops
    0.63
     cell
    0.62
    onest
    0.62
    909
    0.61
    Act Density 0.028%

    No Known Activations