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

    Neuronpedia

    INDEX
    Explanations

    terms related to eligibility and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rolid
    -0.69
    washingtonpost
    -0.68
    robin
    -0.66
    ServiceName
    -0.65
    widetilde
    -0.64
     Meld
    -0.64
     Spirits
    -0.64
     lautet
    -0.63
    Watermark
    -0.63
    Royce
    -0.61
    POSITIVE LOGITS
     hom
    0.93
     Hackney
    0.87
    Nick
    0.86
     Nick
    0.83
    Hom
    0.83
     heter
    0.81
     Heidegger
    0.81
     outono
    0.80
    Haiti
    0.77
     Haiti
    0.76
    Act Density 0.100%

    No Known Activations