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

    Neuronpedia

    INDEX
    Explanations

    keywords that indicate importance or relevance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cket
    -0.17
    á»ijc
    -0.16
    rd
    -0.16
    undra
    -0.15
     Milf
    -0.15
    .ISupportInitialize
    -0.14
    riteln
    -0.14
     имÑĥ
    -0.14
    ownik
    -0.14
     jich
    -0.14
    POSITIVE LOGITS
    cbd
    0.14
    nze
    0.14
    ãģ©
    0.14
    PFN
    0.14
    º
    0.14
     infinite
    0.13
    ï
    0.13
    .boost
    0.13
    âĢIJ
    0.13
    価
    0.13
    Act Density 0.104%

    No Known Activations