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

    Neuronpedia

    INDEX
    Explanations

    information about historical places or events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapto
    -0.94
     solidar
    -0.89
     toal
    -0.86
     demen
    -0.85
     notor
    -0.85
     utop
    -0.82
     hamburg
    -0.81
     hoj
    -0.79
     hek
    -0.76
     ideolog
    -0.76
    POSITIVE LOGITS
     Hence
    0.64
     Thus
    0.63
     Therefore
    0.62
     Thereafter
    0.61
     The
    0.61
     Later
    0.60
     Now
    0.60
     Subsequently
    0.60
     This
    0.60
     Centuries
    0.59
    Act Density 0.577%

    No Known Activations