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

    Neuronpedia

    INDEX
    Explanations

    references to places or entities named "Little"

    oai_token-act-pair · gpt-3.5-turbo

    sections that contain descriptions of fictional creatures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.75
    inates
    -0.71
    iety
    -0.71
    ically
    -0.70
     polarized
    -0.68
    iership
    -0.67
    inate
    -0.66
    ICS
    -0.65
    atically
    -0.64
    ics
    -0.64
    POSITIVE LOGITS
    finger
    1.05
     Mermaid
    0.87
    john
    0.87
     Debbie
    0.81
     Creatures
    0.80
    woods
    0.80
     Sisters
    0.78
    Brother
    0.78
     Havana
    0.78
    foot
    0.75
    Act Density 0.022%

    No Known Activations