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

    Neuronpedia

    INDEX
    Explanations

    descriptions of grandeur and size, especially related to physical structures

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of large physical structures or significant attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zig
    -0.79
    uel
    -0.77
    ective
    -0.76
    ãĥ£
    -0.73
    treatment
    -0.71
    ¹
    -0.71
    earcher
    -0.71
    reb
    -0.71
    leeve
    -0.70
    VR
    -0.69
    POSITIVE LOGITS
     tremend
    1.05
     towering
    1.04
     ceilings
    1.02
     tallest
    0.94
     stature
    0.93
     heights
    0.89
     pomp
    0.87
     majestic
    0.84
     imposing
    0.83
     misunder
    0.79
    Act Density 0.035%

    No Known Activations