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

    Neuronpedia

    INDEX
    Explanations

    emotional dynamics and relationships between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANTLR
    -0.52
     urgencia
    -0.51
    setVerticalGroup
    -0.50
    logne
    -0.49
     szóci
    -0.49
    middels
    -0.47
    <bos>
    -0.46
     realise
    -0.45
    摘要
    -0.44
     MainAxisSize
    -0.44
    POSITIVE LOGITS
     inaccessible
    0.82
     impenetrable
    0.77
     locked
    0.74
     tight
    0.74
     inacces
    0.72
     محفوظة
    0.71
     Stuck
    0.70
     restrictions
    0.69
     restriction
    0.69
     tightly
    0.68
    Act Density 0.549%

    No Known Activations