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

    Neuronpedia

    INDEX
    Explanations

    references to different historical periods or eras

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
      
    -0.57
    Object
    -0.51
    Merken
    -0.50
     
    -0.49
    пли
    -0.48
     steg
    -0.47
    er
    -0.46
    1
    -0.46
     from
    -0.46
     this
    -0.45
    POSITIVE LOGITS
     Epoch
    1.13
     Era
    1.02
     EPO
    0.99
     epochs
    0.95
     epoch
    0.92
     era
    0.89
     ERA
    0.88
    loài
    0.87
    Era
    0.86
     getVersion
    0.85
    Act Density 0.029%

    No Known Activations