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

    Neuronpedia

    INDEX
    Explanations

    repeated elements or common themes in different types of content

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to recurring themes and essential elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oops
    -0.67
    eneg
    -0.63
    agate
    -0.62
    ignt
    -0.61
    odes
    -0.60
    iris
    -0.60
    apor
    -0.59
    brids
    -0.59
     Architects
    -0.58
    ffen
    -0.58
    POSITIVE LOGITS
     amongst
    1.10
     among
    1.04
     throughout
    1.00
     centerpiece
    0.85
    among
    0.83
     fodder
    0.76
     whenever
    0.76
     fixture
    0.76
     across
    0.74
     attraction
    0.73
    Act Density 0.214%

    No Known Activations