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

    Neuronpedia

    INDEX
    Explanations

    narrative elements related to character emotions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dahi
    -0.15
    ighbor
    -0.15
    ÙħÙĦ
    -0.15
    çĶļ
    -0.15
    ereotype
    -0.15
    aint
    -0.15
    allenge
    -0.14
     Åŀah
    -0.14
    egan
    -0.14
    nano
    -0.14
    POSITIVE LOGITS
    nger
    0.14
    Ñĥл
    0.14
     dick
    0.14
    ãģķãģ¾
    0.13
     Unters
    0.13
     киÑĪ
    0.13
    çģ
    0.13
    orias
    0.13
    微软éĽħé»ij
    0.13
    atel
    0.13
    Act Density 0.003%

    No Known Activations