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

    Neuronpedia

    INDEX
    Explanations

    specific household items and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assi
    -0.15
    ħ
    -0.15
     Defined
    -0.14
    vrier
    -0.14
    673
    -0.14
     outer
    -0.14
     involved
    -0.14
    ĥ
    -0.14
     centered
    -0.14
     rooted
    -0.13
    POSITIVE LOGITS
     that
    0.26
    that
    0.26
     made
    0.25
     purchased
    0.20
     capable
    0.20
    made
    0.20
     bought
    0.19
     called
    0.18
    	that
    0.18
     whose
    0.18
    Act Density 0.669%

    No Known Activations