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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or directives related to tasks or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.19
    AWN
    -0.16
    lä
    -0.16
    uchi
    -0.16
    zug
    -0.16
    apore
    -0.15
    anca
    -0.15
    ernen
    -0.15
     Colony
    -0.15
     Zum
    -0.14
    POSITIVE LOGITS
     expect
    0.20
    angler
    0.15
     Expect
    0.15
     expectation
    0.15
     EXPECT
    0.15
    edo
    0.14
    aghan
    0.14
    expects
    0.14
    expect
    0.14
    ess
    0.14
    Act Density 0.046%

    No Known Activations