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

    Neuronpedia

    INDEX
    Explanations

    references to personal or collective relationships and community connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    667
    -0.16
     himself
    -0.15
     oneself
    -0.15
    PLY
    -0.14
    ig
    -0.14
    алеж
    -0.14
    ruise
    -0.14
     Himself
    -0.14
     itself
    -0.14
    owed
    -0.13
    POSITIVE LOGITS
     others
    0.28
     Others
    0.23
    Others
    0.22
    others
    0.22
     anyone
    0.20
     anybody
    0.17
     Anyone
    0.16
     society
    0.16
     everyone
    0.15
     millions
    0.15
    Act Density 0.100%

    No Known Activations