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

    Neuronpedia

    INDEX
    Explanations

    keywords related to general concepts and ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal issues and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Picks
    -0.74
    ĺ
    -0.68
    Broad
    -0.68
    Fat
    -0.65
     Crate
    -0.65
    scl
    -0.64
    Morning
    -0.63
    cedes
    -0.63
    Commun
    -0.62
     =================================
    -0.62
    POSITIVE LOGITS
     overlap
    0.91
     somew
    0.88
     shortage
    0.84
     mismatch
    0.81
     waiting
    0.81
     lurking
    0.80
     difference
    0.76
     temptation
    0.76
     hiding
    0.74
     discrepancy
    0.73
    Act Density 0.317%

    No Known Activations