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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific locations

    oai_token-act-pair · gpt-3.5-turbo

    specific names and titles, particularly associated with locations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.88
     wise
    -0.76
    selves
    -0.74
    theless
    -0.74
     extraord
    -0.70
     sanity
    -0.70
     istg
    -0.70
     partName
    -0.67
     LAST
    -0.65
     Extras
    -0.65
    POSITIVE LOGITS
    onian
    1.27
    ocene
    1.04
    ospels
    0.95
    opian
    0.93
    osphere
    0.93
    venth
    0.91
    leys
    0.90
    orian
    0.88
    waters
    0.87
    ilian
    0.86
    Act Density 0.321%

    No Known Activations