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

    Neuronpedia

    INDEX
    Explanations

    statements introducing a conditional scenario

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.73
    \">
    -0.69
     Highlights
    -0.68
     largeDownload
    -0.67
    Comments
    -0.65
     Estimates
    -0.65
    ãĤ´ãĥ³
    -0.63
     Prior
    -0.62
    DS
    -0.62
    locks
    -0.61
    POSITIVE LOGITS
    nt
    0.92
     indeed
    0.89
     going
    0.82
     truly
    0.82
     gonna
    0.81
     able
    0.81
     sufficiently
    0.80
     configured
    0.77
     properly
    0.77
     inclined
    0.76
    Act Density 0.161%

    No Known Activations