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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or categories of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     those
    -0.75
    those
    -0.70
     stuff
    -0.69
    stuff
    -0.67
     forskning
    -0.66
     Ausrüstung
    -0.64
     legislation
    -0.63
    )_/¯
    -0.63
     Kleidung
    -0.63
     Stuff
    -0.62
    POSITIVE LOGITS
     days
    0.85
     two
    0.85
     kinds
    0.82
     guys
    0.80
     sorts
    0.80
     same
    0.79
    zelfde
    0.79
    cond
    0.76
     three
    0.76
     latter
    0.72
    Act Density 0.328%

    No Known Activations