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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating inclusivity or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;height
    -0.28
     heights
    -0.23
     hardware
    -0.23
     height
    -0.22
    ,height
    -0.21
     hearings
    -0.21
    	height
    -0.20
    .height
    -0.20
     hatred
    -0.19
     hunters
    -0.19
    POSITIVE LOGITS
     tails
    0.18
    Hum
    0.17
     Hum
    0.16
     unh
    0.15
     Senate
    0.15
    els
    0.14
     ног
    0.14
    /xhtml
    0.14
    HT
    0.14
    VBoxLayout
    0.14
    Act Density 0.129%

    No Known Activations