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

    Neuronpedia

    INDEX
    Explanations

    instances of specific nouns, especially in the context of formal agreements and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endale
    -0.15
    agna
    -0.14
     determined
    -0.14
    orida
    -0.14
     respectively
    -0.14
    adol
    -0.14
    iore
    -0.14
    awei
    -0.14
    icle
    -0.14
    lein
    -0.14
    POSITIVE LOGITS
    istrovstvÃŃ
    0.17
    /API
    0.15
    Blockly
    0.15
    aset
    0.15
    arp
    0.15
     Wig
    0.15
    >NN
    0.15
    Forgery
    0.14
    YLON
    0.14
    iert
    0.14
    Act Density 0.018%

    No Known Activations