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

    Neuronpedia

    INDEX
    Explanations

    formal language related to political affiliations and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enquiry
    -0.58
     Whilst
    -0.57
    Whilst
    -0.55
    AnimationsModule
    -0.54
     whilst
    -0.52
     InputDecoration
    -0.51
     majeure
    -0.50
     neighbourhoods
    -0.50
     cze
    -0.49
     enquire
    -0.49
    POSITIVE LOGITS
    yntaxException
    0.80
     الرياضيه
    0.71
    الحياه
    0.63
    Enllaços
    0.60
     Autorizaciones
    0.59
    цездатний
    0.58
    ApiModel
    0.58
    BeginContext
    0.57
    oa̍t
    0.57
    Tracce
    0.57
    Act Density 0.262%

    No Known Activations