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

    Neuronpedia

    INDEX
    Explanations

    references to protests and conflict-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     обоÑĢ
    -0.14
     interess
    -0.14
    isi
    -0.13
     thôi
    -0.13
     interesting
    -0.13
    sounds
    -0.13
    OLE
    -0.13
     prohibited
    -0.13
     Insets
    -0.13
    .abstract
    -0.13
    POSITIVE LOGITS
     perceived
    0.29
     treatment
    0.27
     decision
    0.26
     decisions
    0.25
     lack
    0.24
     recent
    0.23
     handling
    0.23
    æī±
    0.22
     plan
    0.22
     alleged
    0.22
    Act Density 0.228%

    No Known Activations