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

    Neuronpedia

    INDEX
    Explanations

    references to cliffs

    oai_token-act-pair · gpt-3.5-turbo

    references to cliffs, both literal and metaphorical

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Role
    -0.90
    Interstitial
    -0.81
    rity
    -0.79
    abol
    -0.74
    alg
    -0.72
    ulton
    -0.71
    National
    -0.70
    apolis
    -0.69
    arel
    -0.66
    omics
    -0.66
    POSITIVE LOGITS
     cliff
    1.20
     cliffs
    1.05
    =-=-
    0.84
     Cliff
    0.84
     ledge
    0.84
     bluff
    0.84
     dwellings
    0.83
     concession
    0.83
     slope
    0.82
     Dwell
    0.81
    Act Density 0.007%

    No Known Activations