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

    Neuronpedia

    INDEX
    Explanations

    references to entertainment-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    axies
    -0.16
    вали
    -0.15
    asti
    -0.15
    hiba
    -0.14
     Serif
    -0.14
     groceries
    -0.14
    ÃŃcÃŃ
    -0.14
    VERR
    -0.13
    rase
    -0.13
    uti
    -0.13
    POSITIVE LOGITS
     Sung
    0.17
    lord
    0.17
    eway
    0.15
    essian
    0.15
    pj
    0.14
    beg
    0.14
     fond
    0.14
    by
    0.14
     двоÑĢ
    0.13
    DN
    0.13
    Act Density 0.000%

    No Known Activations