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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs indicating action

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their opinions or actions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     juven
    -0.76
    ãĥĺ
    -0.60
    Appearances
    -0.57
     Eisen
    -0.56
    ãģ£
    -0.55
    åħī
    -0.54
     contribut
    -0.53
     Priv
    -0.53
     Breaker
    -0.53
    lining
    -0.53
    POSITIVE LOGITS
     want
    1.54
     desire
    1.53
     wants
    1.38
    want
    1.37
     wish
    1.37
     wished
    1.33
     desires
    1.33
     wanted
    1.33
     Want
    1.32
     desired
    1.30
    Act Density 0.617%

    No Known Activations