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

    Neuronpedia

    INDEX
    Explanations

    the name "Eve"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Eve" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceutical
    -0.83
    enegger
    -0.76
    Americans
    -0.72
    channelAvailability
    -0.69
    omo
    -0.67
    lime
    -0.65
    ains
    -0.65
    oho
    -0.64
    ockey
    -0.63
    ooks
    -0.61
    POSITIVE LOGITS
    lyn
    1.22
    rette
    1.15
     Eve
    0.97
     Valkyrie
    0.95
    lla
    0.93
    lynn
    0.91
    llers
    0.88
    ilon
    0.85
    lling
    0.84
    ller
    0.81
    Act Density 0.031%

    No Known Activations