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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference individuals or groups of people with specific characteristics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ê°ľë¥¼
    -0.18
    tright
    -0.15
    ceph
    -0.14
    ebi
    -0.14
    ogn
    -0.14
    esse
    -0.14
    à¤Ĥà¤Ł
    -0.14
    GED
    -0.14
    ity
    -0.13
    ancement
    -0.13
    POSITIVE LOGITS
     whom
    0.26
     regard
    0.19
     disabilities
    0.18
    stood
    0.17
     whose
    0.15
     access
    0.15
     intact
    0.15
    zik
    0.15
    aid
    0.15
     experience
    0.15
    Act Density 0.051%

    No Known Activations