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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and verb forms indicating identity or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERCHANT
    -0.17
    lover
    -0.17
    blast
    -0.16
    Ùĥار
    -0.15
    ERSION
    -0.15
     neust
    -0.15
    idor
    -0.15
    ãĤĥ
    -0.15
    missive
    -0.15
    acular
    -0.14
    POSITIVE LOGITS
     going
    0.23
     finished
    0.20
     worth
    0.19
     cool
    0.19
     gonna
    0.18
     Cool
    0.18
     dead
    0.18
     Mine
    0.17
     too
    0.17
     OK
    0.17
    Act Density 0.228%

    No Known Activations