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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to ideas, concepts, or plans

    oai_token-act-pair · gpt-3.5-turbo

    sentences that assert or convey the existence of an idea or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.86
     wast
    -0.69
     servicing
    -0.68
     schedule
    -0.68
    athi
    -0.67
    dig
    -0.65
    bill
    -0.64
     dumps
    -0.62
     servic
    -0.62
     Schedule
    -0.61
    POSITIVE LOGITS
     Architects
    0.79
    »Ĵ
    0.73
    ãĥ¼ãĥĨ
    0.72
    uyomi
    0.71
    ãĤ£
    0.70
    ofer
    0.70
    soType
    0.69
    umar
    0.69
    uin
    0.68
     extrap
    0.68
    Act Density 0.661%

    No Known Activations