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

    Neuronpedia

    INDEX
    Explanations

    references to magnitude in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inelli
    -0.80
    haw
    -0.77
    icion
    -0.75
    ilage
    -0.74
    join
    -0.73
    ohydrate
    -0.73
    gotten
    -0.73
    tek
    -0.73
    nell
    -0.72
     Stain
    -0.72
    POSITIVE LOGITS
     magnitude
    1.14
     proportions
    0.86
     scale
    0.86
     impact
    0.82
     anomaly
    0.77
     variance
    0.76
     significance
    0.75
     equival
    0.74
     earthquake
    0.74
     unseen
    0.72
    Act Density 0.010%

    No Known Activations