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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaboration or connection between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .tell
    -0.15
    âng
    -0.15
    lsi
    -0.15
    rien
    -0.14
    atte
    -0.14
    CG
    -0.14
    orsi
    -0.13
    .detect
    -0.13
    .Flags
    -0.13
    acker
    -0.13
    POSITIVE LOGITS
    ENA
    0.17
    ano
    0.16
    ena
    0.15
    è¨
    0.15
     Zwe
    0.14
    ramento
    0.14
    aser
    0.14
    vyk
    0.14
    egan
    0.14
    ãĤ¦ãĥ³
    0.13
    Act Density 0.131%

    No Known Activations