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

    Neuronpedia

    INDEX
    Explanations

    geographical locations or state identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surla
    -1.05
    %");
    -0.90
    WriteBarrier
    -0.83
    findpost
    -0.81
    %"),
    -0.80
    %")
    -0.80
     ModelExpression
    -0.79
     }}$}
    -0.79
    =").
    -0.75
    %?
    -0.74
    POSITIVE LOGITS
    .,
    0.65
     USA
    0.61
    area
    0.52
    USA
    0.51
    IntoConstraints
    0.49
    ulele
    0.47
    .
    0.46
    US
    0.44
     neighborhood
    0.43
    int
    0.43
    Act Density 0.173%

    No Known Activations