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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating collective responsibility or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.87
    MpServer
    -0.82
    catentry
    -0.71
    Sharp
    -0.67
    Magikarp
    -0.63
    NetMessage
    -0.62
     Suite
    -0.62
    Ô
    -0.62
    Reviewer
    -0.60
    pedia
    -0.58
    POSITIVE LOGITS
     hadn
    1.18
     weren
    1.11
     ever
    1.11
     were
    0.95
     wished
    0.94
     wanted
    0.94
     succeeds
    0.93
     succeed
    0.92
     fails
    0.92
     cared
    0.91
    Act Density 0.149%

    No Known Activations