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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to steadfast individuals or entities, often characterized as "stalwarts."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruct
    -0.70
    VERTIS
    -0.69
    yre
    -0.68
     Cause
    -0.67
    åº
    -0.67
     Ik
    -0.64
    EMP
    -0.64
    ITNESS
    -0.63
    holiday
    -0.63
    åħī
    -0.62
    POSITIVE LOGITS
    emate
    0.98
    atural
    0.90
    ataka
    0.88
    nen
    0.88
    otomy
    0.87
    otaur
    0.85
    stal
    0.80
    atory
    0.78
    icum
    0.78
    sters
    0.76
    Act Density 0.094%

    No Known Activations