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

    Neuronpedia

    INDEX
    Explanations

    concepts related to leadership, ethics, and societal values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nÃło
    -0.18
    .setHeight
    -0.15
    oi
    -0.14
    createForm
    -0.14
    .ease
    -0.14
    ODY
    -0.14
    cplusplus
    -0.14
    .tpl
    -0.13
    Ñģклад
    -0.13
     Truly
    -0.13
    POSITIVE LOGITS
     even
    0.31
    even
    0.24
     sogar
    0.24
     EVEN
    0.22
     даже
    0.22
     both
    0.20
     enough
    0.20
     Even
    0.20
     nawet
    0.20
     although
    0.20
    Act Density 0.008%

    No Known Activations