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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concepts or ideas

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dayName
    -0.82
    enegger
    -0.71
    hement
    -0.71
     depended
    -0.67
    )]
    -0.66
    vine
    -0.66
    eches
    -0.65
    iaries
    -0.64
    etz
    -0.64
    athering
    -0.63
    POSITIVE LOGITS
     what
    0.80
    ãģĻ
    0.78
     course
    0.77
     how
    0.74
    rium
    0.69
    reality
    0.69
     morality
    0.69
     sexuality
    0.69
     sorts
    0.68
     masculinity
    0.67
    Act Density 0.152%

    No Known Activations