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

    Neuronpedia

    INDEX
    Explanations

    locations or places, specifically islands

    oai_token-act-pair · gpt-3.5-turbo

    references to islands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acher
    -0.86
    chel
    -0.86
    older
    -0.83
    pheus
    -0.80
    umers
    -0.76
    baugh
    -0.74
    chen
    -0.72
    NRS
    -0.70
    rations
    -0.70
    DIT
    -0.69
    POSITIVE LOGITS
     island
    1.09
     Islands
    1.03
     Island
    0.97
     paradise
    0.93
     islands
    0.91
     hopping
    0.86
     Hispan
    0.84
     Royale
    0.83
    ishly
    0.77
     Islanders
    0.77
    Act Density 0.013%

    No Known Activations