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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant effects or impacts

    oai_token-act-pair · gpt-3.5-turbo

    expressions relating to significant impacts or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atism
    -0.70
    claimer
    -0.69
    ighting
    -0.67
    chwitz
    -0.67
     Lists
    -0.66
    pointers
    -0.65
    classes
    -0.63
     Practices
    -0.63
     Races
    -0.63
    phia
    -0.62
    POSITIVE LOGITS
     impact
    1.52
     effect
    1.50
     ripple
    1.36
     impacts
    1.28
     detrimental
    1.24
     effects
    1.23
     repercussions
    1.21
     affect
    1.19
     adverse
    1.16
     casc
    1.16
    Act Density 0.151%

    No Known Activations