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

    Neuronpedia

    INDEX
    Explanations

    adjectives that convey quality or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ama
    -0.17
    ivery
    -0.17
     feat
    -0.15
    anzi
    -0.14
    ezi
    -0.14
    828
    -0.14
     McKay
    -0.14
    ico
    -0.14
    aku
    -0.13
    ourke
    -0.13
    POSITIVE LOGITS
     reason
    0.23
     chance
    0.21
    лан
    0.17
     danger
    0.17
     limit
    0.17
     possibility
    0.17
     disconnect
    0.16
    GetName
    0.15
     Chance
    0.15
    likelihood
    0.15
    Act Density 0.070%

    No Known Activations