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

    Neuronpedia

    INDEX
    Explanations

    expressions of expectations and qualifications regarding experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otto
    -0.15
    彦
    -0.15
    ilst
    -0.14
    ivid
    -0.14
    zza
    -0.14
    oto
    -0.14
    otal
    -0.14
    aben
    -0.14
    acos
    -0.14
     actionTypes
    -0.14
    POSITIVE LOGITS
     expect
    0.92
    expect
    0.81
     Expect
    0.80
     expectation
    0.80
     expects
    0.76
     EXPECT
    0.76
     expectations
    0.74
     expected
    0.73
    Expect
    0.72
     expecting
    0.69
    Act Density 0.218%

    No Known Activations