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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its variations indicating purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.81
     Monfieur
    -0.75
    الحياه
    -0.73
     charmed
    -0.72
     againſt
    -0.69
     للاسماء
    -0.68
     themſelves
    -0.67
    Personendaten
    -0.67
     asunder
    -0.67
    спасибо
    -0.67
    POSITIVE LOGITS
     be
    0.96
     become
    0.82
     have
    0.79
     actually
    0.65
     eventually
    0.63
     also
    0.63
    uanya
    0.62
    HttpDelete
    0.62
     still
    0.61
     suddenly
    0.60
    Act Density 0.158%

    No Known Activations