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

    Neuronpedia

    INDEX
    Explanations

    references to horses and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eration
    -0.18
    lain
    -0.18
    enty
    -0.15
    راÙģ
    -0.15
     dog
    -0.15
    orp
    -0.15
    ewis
    -0.15
    enance
    -0.15
    ests
    -0.14
    617
    -0.14
    POSITIVE LOGITS
    hair
    0.27
    back
    0.27
    men
    0.25
    power
    0.23
    play
    0.20
    fly
    0.20
    BACK
    0.20
    hoe
    0.20
    women
    0.20
     stable
    0.19
    Act Density 0.013%

    No Known Activations