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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals involved in political or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ighty
    -0.59
     Sovereign
    -0.56
     Newtown
    -0.56
     Cannes
    -0.52
     UT
    -0.52
     Seek
    -0.52
    aukee
    -0.51
    Americ
    -0.51
     Uni
    -0.51
    duc
    -0.51
    POSITIVE LOGITS
     died
    0.81
     countered
    0.79
     reciproc
    0.78
     meanwhile
    0.77
     himself
    0.76
    's
    0.75
     responded
    0.74
     herself
    0.73
     succumbed
    0.72
     disagreed
    0.69
    Act Density 0.305%

    No Known Activations