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

    Neuronpedia

    INDEX
    Explanations

    discussed features or characteristics of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.61
    лой
    -0.59
    aryen
    -0.51
    boe
    -0.50
    '
    -0.50
     руку
    -0.49
    pecies
    -0.48
     D
    -0.48
    equip
    -0.48
    ̀ng
    -0.48
    POSITIVE LOGITS
     Aspects
    1.15
    aspects
    1.06
    tagHelperRunner
    1.03
     Aspect
    1.01
     ASPECTS
    0.99
     betweenstory
    0.98
    Aspects
    0.98
    aspetto
    0.96
     aspects
    0.94
     perspec
    0.83
    Act Density 0.096%

    No Known Activations