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

    Neuronpedia

    INDEX
    Explanations

    concepts related to politics and accountability in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orney
    -0.15
    ?url
    -0.14
    agn
    -0.14
    oret
    -0.14
    elman
    -0.14
    uje
    -0.14
    ếp
    -0.13
    asıyla
    -0.13
    etak
    -0.13
    ola
    -0.13
    POSITIVE LOGITS
     breeds
    0.21
     itself
    0.19
     proceeds
    0.18
     Proceed
    0.18
     breed
    0.18
     existed
    0.18
     need
    0.18
     flour
    0.17
     thr
    0.17
     exact
    0.16
    Act Density 0.442%

    No Known Activations