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

    Neuronpedia

    INDEX
    Explanations

    key aspects of character relationships and societal roles in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unning
    -0.15
    379
    -0.15
    rech
    -0.14
    peare
    -0.14
     Twice
    -0.14
    chin
    -0.14
    ofire
    -0.14
    agens
    -0.14
     Tomorrow
    -0.13
    ffa
    -0.13
    POSITIVE LOGITS
     then
    0.65
     ÑĤогда
    0.57
    then
    0.54
     tehdy
    0.54
     back
    0.52
     THEN
    0.51
     entonces
    0.50
     ëĭ¹ìĭľ
    0.48
     Then
    0.47
    Then
    0.47
    Act Density 0.518%

    No Known Activations