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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to women's issues and empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibrary
    -0.56
     Aval
    -0.54
    ikk
    -0.53
    tz
    -0.51
    tch
    -0.51
    wang
    -0.51
     Yiannopoulos
    -0.50
    cture
    -0.49
     Bannon
    -0.48
     Kaplan
    -0.47
    POSITIVE LOGITS
     alike
    1.42
     thereof
    1.07
     respectively
    1.02
     accordingly
    0.95
     versa
    0.88
     thereafter
    0.79
     therein
    0.74
     thereto
    0.74
    depending
    0.70
     conduc
    0.63
    Act Density 2.160%

    No Known Activations