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

    Neuronpedia

    INDEX
    Explanations

    surface-related terms or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to "surface" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enne
    -0.84
    eros
    -0.83
    rams
    -0.81
    orn
    -0.73
    avering
    -0.73
    orns
    -0.71
    umar
    -0.71
    anders
    -0.70
    endo
    -0.70
    naire
    -0.70
    POSITIVE LOGITS
    FACE
    0.84
    tenance
    0.81
    facing
    0.81
     layer
    0.79
     combatants
    0.77
     mount
    0.76
     coating
    0.75
     area
    0.72
     waters
    0.70
     surface
    0.70
    Act Density 0.046%

    No Known Activations