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

    Neuronpedia

    INDEX
    Explanations

    references to fictional narratives or literary themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.51
     للاسماء
    -0.51
    //
    -0.50
     Roskov
    -0.45
    drawal
    -0.45
     kaarangay
    -0.45
    EndInit
    -0.44
     GenerationType
    -0.44
     bedienen
    -0.44
     onCreateView
    -0.42
    POSITIVE LOGITS
     mention
    1.54
     comment
    1.53
     comments
    1.49
     mentioning
    1.47
     explanation
    1.47
     mentions
    1.42
     explain
    1.38
     explaining
    1.38
     saying
    1.38
     description
    1.36
    Act Density 1.649%

    No Known Activations