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

    Neuronpedia

    INDEX
    Explanations

    strong adjectives that convey intensity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iston
    -0.19
    adelphia
    -0.16
    wise
    -0.16
    ickle
    -0.15
    usercontent
    -0.15
    ufig
    -0.15
    eless
    -0.14
    adil
    -0.14
    ibold
    -0.14
    holm
    -0.14
    POSITIVE LOGITS
     Dolphin
    0.14
     Lucia
    0.13
    _nbr
    0.13
    á»ĩu
    0.13
    atri
    0.13
    ologies
    0.13
    åĽ³
    0.13
    imos
    0.13
     Fle
    0.13
     Zak
    0.13
    Act Density 0.310%

    No Known Activations