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

    Neuronpedia

    INDEX
    Explanations

    code related to function definitions and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    httphttps
    -0.80
    GHIJKLM
    -0.66
     onOptions
    -0.66
    DoubleQuotes
    -0.65
     StringTokenizer
    -0.65
    GrantedAuthority
    -0.60
    NOPQRST
    -0.59
    ViewFeatures
    -0.59
    ratulations
    -0.57
     ddelweddau
    -0.55
    POSITIVE LOGITS
     attacc
    0.49
    ppon
    0.46
    kat
    0.46
     vultures
    0.46
     Hurricane
    0.45
     insuffisamment
    0.45
     McManus
    0.45
     disjoint
    0.44
     asciug
    0.44
     quadros
    0.44
    Act Density 0.527%

    No Known Activations