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

    Neuronpedia

    INDEX
    Explanations

    programming and database-related terminology and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adele
    -0.18
     Uncomment
    -0.16
    maf
    -0.15
     safety
    -0.15
    ÎĪ
    -0.15
    ROM
    -0.14
    ayas
    -0.14
    ikk
    -0.13
    eyen
    -0.13
    lot
    -0.13
    POSITIVE LOGITS
    ãĥ¼ãĥĭ
    0.18
    erton
    0.17
    SSF
    0.17
     contin
    0.15
    isko
    0.15
    atown
    0.15
    _fence
    0.15
     Consolid
    0.15
    /perl
    0.14
    ê³Ħ
    0.14
    Act Density 0.173%

    No Known Activations