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

    Neuronpedia

    INDEX
    Explanations

    terms related to service-oriented models and their evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.25
     myſelf
    -1.22
    ſelf
    -1.18
    ſelves
    -1.14
     ་་
    -1.11
     Monfieur
    -1.11
     ſind
    -1.08
     themſelves
    -1.05
     Anſ
    -0.99
     uſed
    -0.98
    POSITIVE LOGITS
     V
    0.82
     C
    0.80
     L
    0.79
     v
    0.75
     la
    0.73
     E
    0.72
     T
    0.70
    -
    0.70
     P
    0.70
     N
    0.70
    Act Density 0.916%

    No Known Activations