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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locations or events involving coffins

    oai_token-act-pair · gpt-3.5-turbo

    references to coffee and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ®
    -0.85
     Eisen
    -0.76
     Pog
    -0.69
    ãĥ£
    -0.68
    ãĤº
    -0.67
    ãĥ¤
    -0.65
    Ô
    -0.64
    nis
    -0.64
     Bul
    -0.64
    ãĤ§
    -0.64
    POSITIVE LOGITS
    milo
    0.95
    inders
    0.92
    rontal
    0.90
    eem
    0.87
    iasco
    0.85
    iency
    0.84
    aign
    0.83
    legate
    0.82
    ringe
    0.81
     Coff
    0.80
    Act Density 0.015%

    No Known Activations