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

    Neuronpedia

    INDEX
    Explanations

    objects related to physical items or equipment

    oai_token-act-pair · gpt-3.5-turbo

    objects and items associated with crime and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Commerce
    -0.66
     Interest
    -0.66
     Spending
    -0.64
     Flavoring
    -0.64
     PsyNet
    -0.64
     Universities
    -0.63
     Develop
    -0.63
     Influ
    -0.63
     Nights
    -0.63
     Attend
    -0.62
    POSITIVE LOGITS
     belonged
    0.93
     itself
    0.90
    washer
    0.85
     lasted
    0.79
    ultimate
    0.79
     blades
    0.78
     cutter
    0.77
     generator
    0.76
     portion
    0.74
     disappeared
    0.73
    Act Density 0.454%

    No Known Activations