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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to legal or regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.25
    ed
    -0.23
    ing
    -0.22
    hoff
    -0.20
    и
    -0.19
    hill
    -0.19
    halt
    -0.19
    edu
    -0.19
    edn
    -0.19
    ho
    -0.18
    POSITIVE LOGITS
    ting
    0.28
    tempts
    0.23
    tement
    0.21
    ollah
    0.20
    tempt
    0.19
    ernal
    0.19
    rello
    0.19
    lı
    0.18
    ransition
    0.18
    uration
    0.18
    Act Density 0.104%

    No Known Activations