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

    Neuronpedia

    INDEX
    Explanations

    references to social structures and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aming
    -0.17
    amed
    -0.16
    oure
    -0.15
    afil
    -0.15
    ibur
    -0.15
    usi
    -0.15
    aris
    -0.14
    çak
    -0.14
    ufe
    -0.14
    906
    -0.14
    POSITIVE LOGITS
     interacting
    0.16
    leme
    0.15
     fabric
    0.15
    loo
    0.15
    Thrown
    0.15
    .direct
    0.14
     otherwise
    0.14
     interaction
    0.14
    desc
    0.14
    &q
    0.14
    Act Density 0.009%

    No Known Activations