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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to male and female characters in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    0200
    -0.78
     CLR
    -0.77
    iHUD
    -0.65
    elman
    -0.61
    wards
    -0.60
     DOI
    -0.60
     varying
    -0.60
     Drivers
    -0.59
    optional
    -0.58
    noon
    -0.58
    POSITIVE LOGITS
     deserves
    0.81
     cared
    0.76
     belonged
    0.72
     pus
    0.70
     belongs
    0.70
     knew
    0.70
     ain
    0.69
     existed
    0.69
     cares
    0.68
     thri
    0.66
    Act Density 0.139%

    No Known Activations