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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to string manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comma
    -0.16
     Sachs
    -0.15
     abs
    -0.15
    åŀĤ
    -0.15
    éļľ
    -0.15
    comma
    -0.14
    abs
    -0.14
    eph
    -0.14
    ÙĪز
    -0.14
    etro
    -0.14
    POSITIVE LOGITS
     lower
    0.39
     Lower
    0.38
    lower
    0.35
    Lower
    0.34
     upper
    0.34
     Upper
    0.33
     Camel
    0.33
     camel
    0.32
    camel
    0.31
     LOWER
    0.30
    Act Density 0.225%

    No Known Activations