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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to creation or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.53
     I
    -0.44
     The
    -0.40
     ligand
    -0.39
     i
    -0.39
     A
    -0.38
    reactstrap
    -0.38
     James
    -0.38
      
    -0.38
    suite
    -0.38
    POSITIVE LOGITS
    ſelves
    1.01
     myſelf
    1.00
    tagHelperRunner
    1.00
    EndContext
    0.99
     שוליים
    0.97
     itſelf
    0.95
    Geplaatst
    0.93
     ModelExpression
    0.92
    extAlignment
    0.91
    ſelf
    0.91
    Act Density 0.839%

    No Known Activations