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

    Neuronpedia

    INDEX
    Explanations

    phrases related to long-term actions or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to continuity or ongoing maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plaza
    -0.71
    istry
    -0.70
     Blossom
    -0.68
    onym
    -0.67
     GOODMAN
    -0.66
    shop
    -0.66
    ramid
    -0.63
    atron
    -0.62
    ography
    -0.61
    cube
    -0.61
    POSITIVE LOGITS
    ably
    1.04
     sustained
    0.99
    mental
    0.91
     sustain
    0.86
    ments
    0.85
    nces
    0.82
    ive
    0.82
     sustaining
    0.78
    ly
    0.76
    ency
    0.75
    Act Density 0.031%

    No Known Activations