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

    Neuronpedia

    INDEX
    Explanations

    actions related to explaining, describing, or outlining information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yoksa
    -0.15
     disgr
    -0.14
    ä»ĺãģij
    -0.14
     Clarkson
    -0.14
    bek
    -0.13
    caff
    -0.13
    ause
    -0.13
    IRMWARE
    -0.13
     eiusmod
    -0.13
     Gro
    -0.13
    POSITIVE LOGITS
     how
    0.33
     why
    0.28
     briefly
    0.27
    how
    0.24
     cómo
    0.22
    å¦Ĥä½ķ
    0.22
    why
    0.21
     details
    0.19
    æĢİä¹Ī
    0.19
     detail
    0.19
    Act Density 0.136%

    No Known Activations