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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names of locations and individuals

    oai_token-act-pair · gpt-3.5-turbo

    named entities, specifically focusing on people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usalem
    -1.04
    asus
    -1.04
    anes
    -0.86
    gas
    -0.83
    agall
    -0.79
    etsk
    -0.78
    iffin
    -0.77
    aya
    -0.75
    agos
    -0.75
    berra
    -0.74
    POSITIVE LOGITS
     NEC
    0.73
    pod
    0.72
     rehearsal
    0.70
    lip
    0.67
    eed
    0.67
     horm
    0.66
    */(
    0.63
    ULT
    0.63
    phrine
    0.62
     Sussex
    0.62
    Act Density 0.020%

    No Known Activations