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

    Neuronpedia

    INDEX
    Explanations

    references to various types of weapons and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tle
    -0.19
    enance
    -0.17
    eners
    -0.15
    usz
    -0.15
    tml
    -0.15
    gers
    -0.15
    ownt
    -0.14
    incinn
    -0.14
     Higgins
    -0.14
    icult
    -0.13
    POSITIVE LOGITS
    mith
    0.22
    baÅŁ
    0.16
    chair
    0.16
    nit
    0.15
    idel
    0.14
    uffy
    0.14
    155
    0.14
    rest
    0.14
     Elm
    0.14
    ned
    0.13
    Act Density 0.057%

    No Known Activations