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

    Neuronpedia

    INDEX
    Explanations

    references to proper names and businesses

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "survey"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.76
     supplementary
    -0.71
    phabet
    -0.69
     simultaneous
    -0.67
     immersion
    -0.66
     vigilance
    -0.64
     chopping
    -0.64
     retention
    -0.63
    Downloadha
    -0.63
     duplication
    -0.62
    POSITIVE LOGITS
    vey
    1.21
    ards
    1.06
    bugs
    0.85
    rand
    0.83
    rod
    0.82
    aire
    0.75
    gaard
    0.75
    age
    0.73
    tro
    0.73
    enegger
    0.72
    Act Density 0.007%

    No Known Activations