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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names starting with 'La'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names or entities related to specific places or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poke
    -0.69
    perty
    -0.69
     USL
    -0.65
    nyder
    -0.63
     subtract
    -0.61
     MPH
    -0.60
     tremend
    -0.59
     lifespan
    -0.59
     Adin
    -0.58
    arcity
    -0.57
    POSITIVE LOGITS
    rette
    0.98
    anne
    0.77
    ña
    0.76
    hyde
    0.75
    ère
    0.74
    onen
    0.73
    estine
    0.72
    é
    0.70
    igham
    0.70
    inen
    0.69
    Act Density 0.091%

    No Known Activations