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

    Neuronpedia

    INDEX
    Explanations

    elements related to honesty and interpersonal relationships within a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOR
    -0.16
    ahir
    -0.16
    ala
    -0.15
    aby
    -0.15
    ÛĮا
    -0.15
    å¥Ĺ
    -0.14
    ÑĢож
    -0.14
    amax
    -0.14
    icher
    -0.14
    azaar
    -0.14
    POSITIVE LOGITS
     AND
    0.15
    xe
    0.15
     willingness
    0.14
     willing
    0.14
    482
    0.14
     mặc
    0.14
     McGr
    0.14
    gin
    0.14
     èĩªåĬ¨çĶŁæĪIJ
    0.14
    WSC
    0.13
    Act Density 0.075%

    No Known Activations