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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the impact or influence of something on different entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "affected" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issors
    -0.64
     boasts
    -0.62
    night
    -0.61
    Bride
    -0.60
    cule
    -0.58
    Nice
    -0.58
    sonian
    -0.57
     Mu
    -0.57
     proudly
    -0.56
     boasting
    -0.56
    POSITIVE LOGITS
     affected
    3.79
     impacted
    3.07
     effected
    2.34
    affected
    2.16
     Affect
    2.16
     unaffected
    2.15
     afflicted
    2.09
     harmed
    1.73
    ffect
    1.68
     affects
    1.65
    Act Density 0.015%

    No Known Activations