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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values or measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.05
     Majefty
    -1.01
     purpoſe
    -0.97
     himſelf
    -0.96
    ſelves
    -0.95
     themſelves
    -0.94
     Reſ
    -0.93
     myſelf
    -0.93
    ſelf
    -0.91
     Efq
    -0.89
    POSITIVE LOGITS
     
    0.75
     Se
    0.61
     N
    0.60
    Demografia
    0.56
     gynhyrchwyd
    0.55
     legales
    0.54
     ít
    0.54
     nei
    0.52
     en
    0.50
    Datuak
    0.50
    Act Density 0.299%

    No Known Activations