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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something serves a specific purpose or function

    oai_token-act-pair · gpt-3.5-turbo

    references to roles or functions of objects within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulous
    -0.68
    chev
    -0.66
    rants
    -0.65
     Rebell
    -0.65
    oes
    -0.65
    olds
    -0.63
    TAIN
    -0.63
    REE
    -0.63
    asking
    -0.60
    ron
    -0.59
    POSITIVE LOGITS
     intermediary
    0.89
     interim
    0.87
     catalyst
    0.83
     liaison
    0.83
     an
    0.82
     collateral
    0.82
     inspiration
    0.81
     adjunct
    0.81
     bait
    0.80
     a
    0.79
    Act Density 0.077%

    No Known Activations