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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial and positional references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.93
     Majefty
    -0.92
     iſt
    -0.89
     ―――――
    -0.86
     Houſe
    -0.86
     Jefus
    -0.86
     Efq
    -0.83
     ་་
    -0.83
     myſelf
    -0.82
     Theſe
    -0.80
    POSITIVE LOGITS
     в
    0.79
    В
    0.75
    в
    0.69
     под
    0.67
     В
    0.61
     del
    0.60
    வ்
    0.60
    ↵↵
    0.57
     ใน
    0.57
     the
    0.57
    Act Density 0.013%

    No Known Activations