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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and proper nouns related to places, specifically in the context of news or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.77
    ſelf
    -0.76
     ſmall
    -0.75
     purpoſe
    -0.73
     pleaſure
    -0.71
     ſta
    -0.70
     ſeveral
    -0.70
     ſtate
    -0.69
    AxisAlignment
    -0.66
     perſon
    -0.66
    POSITIVE LOGITS
    locally
    0.57
     <<<<<<<<<<<<<<
    0.57
     בארץ
    0.54
     locally
    0.54
     today
    0.53
     <=",
    0.53
    енча
    0.52
    PerformLayout
    0.51
    iecie
    0.49
     estekak
    0.49
    Act Density 1.012%

    No Known Activations