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

    Neuronpedia

    INDEX
    Explanations

    references to vice or roles associated with authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.59
    下载附件
    -0.59
    ardless
    -0.54
     BoxFit
    -0.54
     TestBed
    -0.52
    Datuak
    -0.52
    igslist
    -0.51
    XtraReports
    -0.50
    Архівовано
    -0.50
    LabelTagHelper
    -0.49
    POSITIVE LOGITS
    Vice
    0.77
     Vice
    0.74
     vice
    0.71
    en
    0.60
    vice
    0.57
    English
    0.55
     françaises
    0.52
     VICE
    0.50
     franceses
    0.49
     French
    0.49
    Act Density 0.188%

    No Known Activations