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

    Neuronpedia

    INDEX
    Explanations

    articles used to introduce nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stance
    -0.15
    .ie
    -0.14
    ama
    -0.14
    ivery
    -0.14
     tÆ°
    -0.14
    verture
    -0.14
    uster
    -0.14
    ово
    -0.14
     feat
    -0.13
    opic
    -0.13
    POSITIVE LOGITS
     reason
    0.26
     chance
    0.23
     saying
    0.23
     difference
    0.21
     temptation
    0.20
     danger
    0.20
     possibility
    0.20
     tendency
    0.19
     need
    0.18
     chances
    0.18
    Act Density 0.079%

    No Known Activations