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

    Neuronpedia

    INDEX
    Explanations

    references to reviewers and their comments in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discussion of reviewers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.70
    tagHelperRunner
    -0.66
    ⓧ
    -0.63
     pleaſure
    -0.62
    Parcelize
    -0.61
     utafitiHapana
    -0.57
    DrawerToggle
    -0.57
     purpoſe
    -0.57
    TagMode
    -0.57
    Portail
    -0.57
    POSITIVE LOGITS
     reviewer
    1.61
     reviewers
    1.50
     Reviewer
    1.48
    reviewer
    1.37
    Reviewer
    1.24
    Reviewers
    1.20
     commenter
    0.71
     interviewer
    0.69
     commentators
    0.68
     columnist
    0.67
    Act Density 0.017%

    No Known Activations