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

    Neuronpedia

    INDEX
    Explanations

    expressions related to coding conventions and string manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pop
    -0.36
     nab
    -0.30
     POP
    -0.30
     Vall
    -0.30
     Pop
    -0.30
    Pop
    -0.29
    pop
    -0.28
     program
    -0.27
     page
    -0.27
    kö
    -0.27
    POSITIVE LOGITS
     prefix
    0.92
    prefix
    0.89
     prefixes
    0.86
     Prefix
    0.85
    Prefix
    0.84
     PREFIX
    0.83
    startsWith
    0.78
    PREFIX
    0.77
     prefixed
    0.77
    startswith
    0.75
    Act Density 0.490%

    No Known Activations