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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate strong performance or capability in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ssf
    -0.15
    cac
    -0.15
    canf
    -0.15
    ãģķãģ¾
    -0.15
    werk
    -0.15
    GRA
    -0.15
    slaught
    -0.14
     datings
    -0.14
     огÑĢа
    -0.14
    osu
    -0.14
    POSITIVE LOGITS
    uzzi
    0.19
     Hav
    0.17
    _dirty
    0.15
    itory
    0.15
    998
    0.15
    794
    0.14
     Riv
    0.14
    666
    0.14
    345
    0.14
     Tro
    0.14
    Act Density 0.278%

    No Known Activations