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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographical locations, particularly 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
    baugh
    -0.96
    chel
    -0.93
    chen
    -0.88
    nyder
    -0.88
    acher
    -0.83
    itbart
    -0.78
    umers
    -0.78
    pheus
    -0.73
    wcsstore
    -0.72
    gio
    -0.72
    POSITIVE LOGITS
     Islands
    1.03
     island
    0.97
     paradise
    0.97
     islands
    0.92
     hopping
    0.91
    walk
    0.84
     Island
    0.82
    wide
    0.82
    ishly
    0.80
     Hispan
    0.78
    Act Density 0.017%

    No Known Activations