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

    Neuronpedia

    INDEX
    Explanations

    phrases related to registration, publication, or organization

    oai_token-act-pair · gpt-3.5-turbo

    past participles related to actions and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Operation
    -0.68
    knife
    -0.65
    acity
    -0.64
    ggles
    -0.63
    tra
    -0.63
    posure
    -0.61
    Shift
    -0.61
     bush
    -0.61
    iots
    -0.61
    roots
    -0.60
    POSITIVE LOGITS
    ĸļ
    0.82
    entious
    0.79
    omorphic
    0.74
     geographically
    0.74
    ertodd
    0.73
     proport
    0.72
    ãĤ´
    0.71
     statically
    0.71
    £ı
    0.70
     by
    0.68
    Act Density 0.327%

    No Known Activations