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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate community and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quo
    -0.16
    elson
    -0.15
     rem
    -0.14
     Trot
    -0.14
    ãĥĥ
    -0.14
     Shell
    -0.14
    220
    -0.13
    Wiki
    -0.13
    que
    -0.13
    atu
    -0.13
    POSITIVE LOGITS
    esome
    0.18
    arty
    0.16
    ienie
    0.15
     sticky
    0.15
    дÑı
    0.14
     Devils
    0.14
    IntPtr
    0.14
    jen
    0.13
     Sticky
    0.13
    intColor
    0.13
    Act Density 0.385%

    No Known Activations