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

    Neuronpedia

    INDEX
    Explanations

    concepts related to website security and spam prevention strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esel
    -0.17
    Specifier
    -0.15
    plication
    -0.14
     chron
    -0.14
     encode
    -0.14
     Chron
    -0.14
    atha
    -0.14
    adio
    -0.13
    FFE
    -0.13
     Desert
    -0.13
    POSITIVE LOGITS
    /block
    0.23
    /black
    0.22
     blacklist
    0.21
     block
    0.20
     Blocked
    0.20
     blocked
    0.20
    _BLOCK
    0.20
    block
    0.19
     Filtering
    0.19
    -block
    0.19
    Act Density 0.053%

    No Known Activations