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

    Neuronpedia

    INDEX
    Explanations

    distinctive patterns or structures in sentence construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¡
    -0.15
    (LP
    -0.15
    æ¬
    -0.14
    umblr
    -0.14
     ÑģобоÑİ
    -0.14
    Bindable
    -0.14
    ERGY
    -0.14
    é¼ĵ
    -0.13
    Blockly
    -0.13
    SSION
    -0.13
    POSITIVE LOGITS
     which
    0.18
     Which
    0.16
    rc
    0.15
    ique
    0.14
    49
    0.14
     ie
    0.13
    443
    0.13
     but
    0.13
     nor
    0.13
     respectively
    0.13
    Act Density 0.088%

    No Known Activations