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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and comment indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unless
    -0.26
    unless
    -0.25
    Unless
    -0.20
     whenever
    -0.19
     Unless
    -0.18
     depending
    -0.18
    depending
    -0.17
     once
    -0.15
    once
    -0.15
     ØŃاÙĦ
    -0.15
    POSITIVE LOGITS
    ;if
    0.22
     If
    0.21
    ãĢĤå¦Ĥæŀľ
    0.20
    .if
    0.19
    If
    0.18
    	if
    0.17
    ázd
    0.17
    å¦Ĥæŀľ
    0.17
    .If
    0.16
    >If
    0.16
    Act Density 0.140%

    No Known Activations