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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific concepts and principles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to scientific principles and history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eligible
    -0.65
    udi
    -0.63
     Category
    -0.62
     Tot
    -0.61
    irgin
    -0.59
    fired
    -0.59
    Saharan
    -0.56
    inel
    -0.56
    arna
    -0.56
    gard
    -0.56
    POSITIVE LOGITS
     behind
    1.69
    behind
    1.46
     Behind
    1.31
     underlying
    1.26
     involved
    1.18
     underpin
    1.17
     surrounding
    1.16
     of
    1.03
     governing
    1.02
     thereof
    0.98
    Act Density 0.266%

    No Known Activations