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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or teams

    oai_token-act-pair · gpt-3.5-turbo

    possessive determiners referring to people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.75
    iability
    -0.73
    trop
    -0.72
    Enabled
    -0.69
    Vers
    -0.69
    availability
    -0.68
    VERTISEMENT
    -0.68
    uncture
    -0.67
    代
    -0.65
    Upload
    -0.65
    POSITIVE LOGITS
     cohorts
    1.09
     colleagues
    1.09
     allies
    1.02
     wife
    0.97
     fellow
    0.93
     friends
    0.92
     mates
    0.92
     pals
    0.90
     buddies
    0.88
     associates
    0.87
    Act Density 0.120%

    No Known Activations