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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues or discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal issues and individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $.
    -0.77
     gobl
    -0.75
     mathemat
    -0.67
     showc
    -0.67
     arrang
    -0.65
     notor
    -0.65
     Niet
    -0.63
     Palestin
    -0.62
     Cairo
    -0.59
     traged
    -0.58
    POSITIVE LOGITS
     meanwhile
    0.69
    ¶
    0.66
     analogy
    0.62
     requires
    0.61
     helps
    0.61
    Community
    0.60
     Yourself
    0.59
     entails
    0.58
     huh
    0.57
     Cause
    0.57
    Act Density 0.866%

    No Known Activations