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

    Neuronpedia

    INDEX
    Explanations

    the article "A" suggesting a focus on specific subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Orient
    -0.66
    arsity
    -0.60
    aneously
    -0.59
     extrad
    -0.59
    Finish
    -0.59
    office
    -0.58
    apesh
    -0.58
     proceedings
    -0.58
    olicy
    -0.56
    soType
    -0.55
    POSITIVE LOGITS
    cknowled
    1.66
    cknow
    1.38
    verages
    1.14
    chie
    1.02
    lyss
    0.98
    usterity
    0.96
     few
    0.96
     downside
    0.94
    chieve
    0.93
     lot
    0.92
    Act Density 0.084%

    No Known Activations