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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures indicating conclusions or summaries in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ίνη
    -0.15
    üst
    -0.15
    à¸Ħร
    -0.13
    à¥įपत
    -0.13
     Begin
    -0.13
    ãĥ³ãĤ¸
    -0.13
    anguard
    -0.13
    èµ·
    -0.13
     forthcoming
    -0.13
     tức
    -0.13
    POSITIVE LOGITS
     ending
    0.77
     finish
    0.71
     ends
    0.70
     ended
    0.68
     finishes
    0.67
     finishing
    0.65
     Ending
    0.63
     concludes
    0.61
     conclude
    0.60
     endings
    0.59
    Act Density 0.244%

    No Known Activations