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

    Neuronpedia

    INDEX
    Explanations

    specific variable names and addresses in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    folk
    -0.81
    phi
    -0.73
    selection
    -0.67
    fol
    -0.65
    runners
    -0.64
    corn
    -0.64
    secut
    -0.63
     Scots
    -0.63
     Hearts
    -0.60
    WARD
    -0.59
    POSITIVE LOGITS
    ynski
    1.19
    arella
    0.94
    ewski
    0.91
    arre
    0.90
    atche
    0.87
    arro
    0.84
    arest
    0.81
    ars
    0.80
    arl
    0.80
    ombie
    0.78
    Act Density 0.004%

    No Known Activations