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

    Neuronpedia

    INDEX
    Explanations

    references to family-related concepts or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.74
    iasis
    -0.68
    igo
    -0.65
     Prom
    -0.65
     Gaul
    -0.63
     Hoover
    -0.63
     Flavoring
    -0.62
    zeb
    -0.62
    Stre
    -0.61
     GDDR
    -0.61
    POSITIVE LOGITS
    chool
    1.10
    folk
    0.96
    hetical
    0.85
    heses
    0.84
    ilies
    0.78
    archs
    0.76
     reun
    0.75
    hesis
    0.72
     bonded
    0.70
    ILY
    0.70
    Act Density 0.019%

    No Known Activations