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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the top portion of objects or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concepts of "top" and "bottom" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naires
    -0.82
    naire
    -0.77
    ãĥīãĥ©
    -0.73
     hunger
    -0.70
    uld
    -0.70
    ibr
    -0.64
    adier
    -0.63
     Pell
    -0.63
    vacc
    -0.62
    ettel
    -0.62
    POSITIVE LOGITS
    most
    1.19
    bottom
    0.86
     membrane
    0.77
    hesis
    0.75
     pane
    0.75
     layer
    0.73
    board
    0.73
    stroke
    0.72
    mast
    0.72
     casing
    0.71
    Act Density 0.039%

    No Known Activations