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

    Neuronpedia

    INDEX
    Explanations

    code-related keywords and expressions, particularly those that involve string manipulation and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.57
    :✨
    -0.52
    tagext
    -0.51
     sher
    -0.50
    gonic
    -0.50
    Sher
    -0.50
    AsyncResult
    -0.49
     panoramique
    -0.48
     BMD
    -0.47
     Sher
    -0.47
    POSITIVE LOGITS
     separator
    1.26
     separated
    1.22
     seper
    1.18
     Separator
    1.17
     separating
    1.16
     Separ
    1.15
     comma
    1.12
    separator
    1.12
     separation
    1.11
    separated
    1.07
    Act Density 0.403%

    No Known Activations