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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific keywords in interviews and other dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azon
    -0.16
    ìĹŃ
    -0.14
    è£ı
    -0.14
    ãĥ¼ãĥĪ
    -0.14
     Rings
    -0.13
     rings
    -0.13
    ستÙĩ
    -0.13
    flen
    -0.13
     rencont
    -0.13
    grave
    -0.13
    POSITIVE LOGITS
    cke
    0.15
     Grat
    0.15
    hei
    0.15
    ovsky
    0.14
    enko
    0.13
    oupper
    0.13
    tek
    0.13
    ivo
    0.13
     unt
    0.13
     СвÑıÑĤ
    0.13
    Act Density 0.028%

    No Known Activations