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

    Neuronpedia

    INDEX
    Explanations

    geographic locations, particularly cities

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations, particularly cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.66
     Bleach
    -0.65
    cession
    -0.64
    ught
    -0.61
     Transformation
    -0.59
     Bin
    -0.59
     Purg
    -0.58
    Jet
    -0.57
     Log
    -0.57
     Priv
    -0.57
    POSITIVE LOGITS
    ANC
    0.90
    INC
    0.89
    IRO
    0.89
    ION
    0.87
     GOODMAN
    0.87
    POST
    0.86
    ANE
    0.86
    OVER
    0.85
    IONS
    0.85
    ICO
    0.84
    Act Density 0.058%

    No Known Activations