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

    Neuronpedia

    INDEX
    Explanations

    references to dogs and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Statue
    -0.54
     Slovakia
    -0.47
     Indoch
    -0.45
    Statue
    -0.45
     amorti
    -0.45
     academy
    -0.43
    stdafx
    -0.43
    ⏜
    -0.43
     Shogun
    -0.43
    forChild
    -0.43
    POSITIVE LOGITS
     dog
    0.93
     Active
    0.70
     cat
    0.61
    OGND
    0.59
     dogs
    0.58
     anjing
    0.56
    AndEndTag
    0.56
    Active
    0.55
     autorytatywna
    0.55
    dog
    0.54
    Act Density 0.195%

    No Known Activations