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

    Neuronpedia

    INDEX
    Explanations

    specific occupations or roles that people may have

    oai_token-act-pair · gpt-3.5-turbo

    specific roles or identities associated with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izens
    -0.72
     architectures
    -0.71
     intervals
    -0.70
    ories
    -0.69
     Lans
    -0.68
     iPads
    -0.67
     Boards
    -0.67
     offenses
    -0.66
    rams
    -0.66
     shocks
    -0.65
    POSITIVE LOGITS
    digy
    0.92
     myself
    0.91
     unto
    0.84
    alyst
    0.84
    iste
    0.81
     herself
    0.81
    ess
    0.79
     someday
    0.78
     himself
    0.77
    nik
    0.75
    Act Density 0.266%

    No Known Activations