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

    Neuronpedia

    INDEX
    Explanations

    references to a specific place or name - "Tahoe"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Tahrir Square."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.77
    ISTER
    -0.70
    ãģķ
    -0.67
     fixation
    -0.65
    mble
    -0.65
    ancial
    -0.64
     psy
    -0.63
     cov
    -0.63
     Parenthood
    -0.63
    ãģĦ
    -0.63
    POSITIVE LOGITS
     Tah
    1.17
    oya
    1.02
    rir
    1.01
    ibia
    0.88
    renheit
    0.85
    iti
    0.84
    aba
    0.82
    ti
    0.81
    ango
    0.81
    essa
    0.80
    Act Density 0.007%

    No Known Activations