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

    Neuronpedia

    INDEX
    Explanations

    descriptors of physical attributes and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'gc
    -0.17
    Occurs
    -0.17
    umbn
    -0.15
    ¶Į
    -0.15
    ãĤĩ
    -0.14
    ลล
    -0.14
    онÑĮ
    -0.14
     )↵↵↵↵↵↵↵↵
    -0.14
    ptal
    -0.14
    .updateDynamic
    -0.14
    POSITIVE LOGITS
     certainly
    0.29
     makes
    0.28
     definitely
    0.28
     is
    0.25
     really
    0.24
     make
    0.24
     speaks
    0.22
     truly
    0.21
     felt
    0.21
     sure
    0.20
    Act Density 0.341%

    No Known Activations