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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to nuclear physics

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and terms related to specific individuals or scientific concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HEAD
    -0.72
    XY
    -0.72
    è¦ļéĨĴ
    -0.71
    WAYS
    -0.68
    headers
    -0.67
    head
    -0.65
     Alz
    -0.63
    DOS
    -0.63
     menstrual
    -0.61
    heads
    -0.60
    POSITIVE LOGITS
    eties
    1.00
    ates
    0.99
    į
    0.97
    eness
    0.97
    ±
    0.94
    ophile
    0.93
    ally
    0.93
    ij
    0.93
    ĭ
    0.93
    als
    0.92
    Act Density 0.040%

    No Known Activations