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

    Neuronpedia

    INDEX
    Explanations

    discussions about rules and societal norms related to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Foundation
    -0.15
    ars
    -0.15
    ork
    -0.15
     Digest
    -0.14
    asis
    -0.14
     tend
    -0.14
    hor
    -0.14
    itler
    -0.13
     nisi
    -0.13
     endwhile
    -0.13
    POSITIVE LOGITS
     irrelevant
    0.40
     matters
    0.32
     matter
    0.32
     mattered
    0.31
     Matters
    0.30
    matter
    0.29
     Matter
    0.28
     concern
    0.26
     Doesn
    0.26
     cares
    0.26
    Act Density 0.288%

    No Known Activations