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

    Neuronpedia

    INDEX
    Explanations

    descriptions of people's backgrounds and professions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to occupations and professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iPads
    -0.74
    iners
    -0.69
     domains
    -0.64
    pps
    -0.64
    uld
    -0.63
    akespe
    -0.62
    éĹĺ
    -0.61
    docs
    -0.60
    ciating
    -0.60
    ouls
    -0.58
    POSITIVE LOGITS
     whose
    1.16
     extraord
    1.13
     who
    1.11
     specializing
    1.09
     nicknamed
    1.05
     whom
    1.03
     residing
    1.00
    whose
    0.96
    Joined
    0.89
     born
    0.88
    Act Density 0.171%

    No Known Activations