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

    Neuronpedia

    INDEX
    Explanations

    terms related to domains in web or internet contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queer
    -1.71
     tear
    -1.69
     transgender
    -1.66
     maternal
    -1.65
     promise
    -1.59
     birth
    -1.56
     miscar
    -1.55
    ights
    -1.54
      ↵
    -1.54
    inher
    -1.53
    POSITIVE LOGITS
    £
    2.73
    ļ
    2.60
    ĸ´
    2.60
    ĸ
    2.58
      ↵
    2.58
    ↵↵
    2.58
    ↵
    2.58
    2.58
    ↵
    2.58
    2.58
    Act Density 0.141%

    No Known Activations