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

    Neuronpedia

    INDEX
    Explanations

    instances of academic study and education-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĿãĤĮãģ¯
    -0.15
    &W
    -0.14
    iry
    -0.14
    cdf
    -0.14
    isten
    -0.14
    stalk
    -0.14
    _closure
    -0.14
    Coverage
    -0.13
    igham
    -0.13
    oir
    -0.13
    POSITIVE LOGITS
     abroad
    0.20
     medicine
    0.19
    vala
    0.17
     law
    0.16
     intens
    0.15
    ymology
    0.15
    ring
    0.14
    æ³ķ
    0.14
    мага
    0.14
    INATION
    0.14
    Act Density 0.037%

    No Known Activations