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

    Neuronpedia

    INDEX
    Explanations

    references to physical geographic features, specifically cliffs

    oai_token-act-pair · gpt-3.5-turbo

    references to cliffs and related metaphors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.91
    apolis
    -0.83
    rity
    -0.79
    ufact
    -0.78
    natureconservancy
    -0.77
    Role
    -0.77
    alties
    -0.76
    ATA
    -0.73
    ãĤ±
    -0.71
    ional
    -0.70
    POSITIVE LOGITS
    haven
    0.83
    cutting
    0.81
     dwellings
    0.80
    hemy
    0.78
    olicy
    0.77
    cut
    0.75
    frog
    0.75
     cliffs
    0.74
    =-=-
    0.72
     Dwell
    0.71
    Act Density 0.066%

    No Known Activations