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

    Neuronpedia

    INDEX
    Explanations

    news articles or publications

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas or punctuation in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Availability
    -0.67
     autop
    -0.63
     appro
    -0.62
    ulz
    -0.61
     fantasies
    -0.61
    ocry
    -0.60
     idols
    -0.57
    ¬¼
    -0.57
    herent
    -0.57
    ãĥ¥
    -0.55
    POSITIVE LOGITS
     however
    1.25
     huh
    1.11
     meanwhile
    1.08
     although
    1.05
     though
    0.98
     albeit
    0.91
     namely
    0.87
     citing
    0.81
     moreover
    0.81
     whereas
    0.78
    Act Density 1.614%

    No Known Activations