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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¤ĩ
    -0.17
    oppins
    -0.16
     FIG
    -0.15
    mani
    -0.15
    ged
    -0.15
     Hell
    -0.14
     Integrity
    -0.14
    quil
    -0.14
    ueil
    -0.14
    primer
    -0.14
    POSITIVE LOGITS
     part
    0.23
    friend
    0.19
    ieve
    0.18
     involved
    0.18
     apart
    0.17
     μÎŃÏģοÏĤ
    0.17
     spontaneous
    0.17
    anz
    0.16
    ause
    0.16
    auf
    0.16
    Act Density 0.133%

    No Known Activations