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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce additional information or details

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce additional information or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jam
    -0.72
    bane
    -0.67
     Orange
    -0.65
    bugs
    -0.65
    bour
    -0.63
    iste
    -0.63
    venge
    -0.62
    irin
    -0.62
     Burlington
    -0.61
    haw
    -0.60
    POSITIVE LOGITS
    olkien
    0.87
     thereto
    0.69
     materially
    0.66
    igm
    0.66
    onga
    0.66
    hesis
    0.66
    ipolar
    0.64
    ulkan
    0.64
     consideration
    0.63
    nyder
    0.63
    Act Density 0.016%

    No Known Activations