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

    Neuronpedia

    INDEX
    Explanations

    mentions of tall objects or structures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "tall"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.89
    eer
    -0.88
    в
    -0.79
    ktop
    -0.78
    eers
    -0.77
    ller
    -0.76
    ruption
    -0.74
    eln
    -0.74
    vernment
    -0.74
    arty
    -0.72
    POSITIVE LOGITS
     stature
    1.12
     taller
    1.03
     tallest
    1.02
     towers
    0.86
    itude
    0.86
     tall
    0.85
     enough
    0.85
     weeds
    0.81
    nesses
    0.80
     scale
    0.80
    Act Density 0.019%

    No Known Activations