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

    Neuronpedia

    INDEX
    Explanations

    names of actors and athletes

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in a context related to achievement or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.75
    ccording
    -0.71
     unfavorable
    -0.66
     therefore
    -0.62
    Firstly
    -0.59
     consequently
    -0.58
     involves
    -0.58
    population
    -0.55
     FANTASY
    -0.54
     differs
    -0.53
    POSITIVE LOGITS
     Jr
    1.28
    hetti
    0.93
     Sr
    0.86
    hoff
    0.85
     III
    0.84
    iak
    0.83
    cki
    0.76
     II
    0.75
    elli
    0.74
    ,
    0.73
    Act Density 0.215%

    No Known Activations