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

    Neuronpedia

    INDEX
    Explanations

    social media links

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.63
     substitutes
    -0.59
    quartered
    -0.59
     Fortune
    -0.58
     successor
    -0.58
    conservancy
    -0.57
     numbering
    -0.56
     recovering
    -0.56
    luster
    -0.56
     outdoors
    -0.55
    POSITIVE LOGITS
    /_
    0.90
    /#
    0.82
    nw
    0.74
    cdn
    0.71
    /?
    0.68
    mAh
    0.67
    Ku
    0.65
    ua
    0.65
    /-
    0.64
    000000
    0.63
    Act Density 0.010%

    No Known Activations