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

    Neuronpedia

    INDEX
    Explanations

    sources or references within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to sources of information or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TAG
    -0.73
    aeper
    -0.71
    osate
    -0.69
    eg
    -0.65
    Interstitial
    -0.64
    ĸļ
    -0.63
    eering
    -0.63
    Laun
    -0.63
    cair
    -0.62
    script
    -0.62
    POSITIVE LOGITS
     sources
    0.86
     informants
    0.83
     knowledgeable
    0.82
     priv
    0.81
     familiar
    0.78
     briefed
    0.77
     consulted
    0.73
     quoted
    0.71
    imate
    0.71
    iances
    0.70
    Act Density 0.027%

    No Known Activations