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

    Neuronpedia

    INDEX
    Explanations

    mentions of the city of Phoenix

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Phoenix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ischer
    -0.77
    abet
    -0.77
    hirt
    -0.76
    redo
    -0.72
    ntil
    -0.71
    oys
    -0.70
    flows
    -0.69
    arger
    -0.68
    apter
    -0.68
    uther
    -0.67
    POSITIVE LOGITS
     Coyotes
    1.17
     Suns
    1.08
     Wright
    0.97
     Rising
    0.90
     Phoenix
    0.88
    Phoenix
    0.84
    angel
    0.82
     AZ
    0.78
    oning
    0.76
    ertodd
    0.74
    Act Density 0.009%

    No Known Activations