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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to choices and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ly
    -0.18
    sole
    -0.18
    thy
    -0.16
     Sole
    -0.16
    prises
    -0.15
    ipa
    -0.15
    hee
    -0.15
    acio
    -0.15
    otos
    -0.14
    rea
    -0.14
    POSITIVE LOGITS
    Made
    0.20
     made
    0.19
    fulness
    0.18
     Made
    0.18
    aint
    0.17
    able
    0.16
    indeki
    0.16
    y
    0.16
    841
    0.15
    lessly
    0.15
    Act Density 0.042%

    No Known Activations