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

    Neuronpedia

    INDEX
    Explanations

    references to promotional offers or discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Lib
    -0.17
    ipple
    -0.15
    odon
    -0.15
     Sage
    -0.15
    .ServiceModel
    -0.14
     Fleming
    -0.14
     rallies
    -0.14
     tire
    -0.14
     Spit
    -0.14
    umper
    -0.13
    POSITIVE LOGITS
     hack
    0.27
    Hack
    0.21
     Hack
    0.21
     generator
    0.21
    hack
    0.20
    -generator
    0.20
     hacks
    0.20
     hacking
    0.19
     hackers
    0.19
     hacker
    0.18
    Act Density 0.000%

    No Known Activations