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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fotografico
    -0.60
     pouvoit
    -0.60
     zijne
    -0.59
     valentín
    -0.59
     méri
    -0.57
     współpracy
    -0.56
     mijne
    -0.55
     dezelve
    -0.54
    ähteet
    -0.53
    EndContext
    -0.52
    POSITIVE LOGITS
     impo
    0.44
     relax
    0.43
    charming
    0.40
    дмила
    0.40
    geslacht
    0.39
    httphttps
    0.39
     

    0.38
     bru
    0.38
     direct
    0.38
     Offshore
    0.38
    Act Density 0.546%

    No Known Activations