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

    Neuronpedia

    INDEX
    Explanations

    references to the term "dog" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aurus
    -0.18
    æ¦ľ
    -0.17
    icks
    -0.16
    ków
    -0.16
    odian
    -0.15
    áÅĻ
    -0.14
    äre
    -0.14
    hots
    -0.14
     recep
    -0.14
    searchModel
    -0.14
    POSITIVE LOGITS
    ged
    0.30
    gy
    0.28
    gie
    0.24
    matic
    0.23
    ma
    0.22
    gett
    0.21
    gone
    0.21
    ger
    0.20
    mat
    0.20
     bark
    0.19
    Act Density 0.016%

    No Known Activations