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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or actions happening in the past

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to controversial or judgmental evaluations of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )).
    -0.66
    é¾įå
    -0.58
    ļé
    -0.56
    rush
    -0.56
    )."
    -0.55
    aldo
    -0.55
    ]).
    -0.54
    CONCLUS
    -0.53
    thouse
    -0.53
    ))))
    -0.52
    POSITIVE LOGITS
    Picture
    0.65
     firsthand
    0.54
    ickr
    0.49
     its
    0.49
    ,[
    0.49
     because
    0.49
     their
    0.48
     overseas
    0.47
     vitro
    0.47
    because
    0.47
    Act Density 1.535%

    No Known Activations