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

    Neuronpedia

    INDEX
    Explanations

    references to specific geographic regions, economic topics, and notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.74
    gencies
    -0.59
    ¯¯¯¯
    -0.57
    encies
    -0.57
    Topics
    -0.56
    ebook
    -0.56
     deductions
    -0.55
    ths
    -0.54
     inputs
    -0.54
    said
    -0.53
    POSITIVE LOGITS
    *.
    0.71
    vertisement
    0.66
    .[
    0.66
    .
    0.64
    !!!!!!!!
    0.64
     itself
    0.62
    ().
    0.59
    _.
    0.58
     whose
    0.58
    !!!!
    0.58
    Act Density 0.405%

    No Known Activations