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

    Neuronpedia

    INDEX
    Explanations

    Twitter links

    oai_token-act-pair · gpt-3.5-turbo

    internet domain names, particularly related to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fortune
    -0.62
     substitutes
    -0.58
    quartered
    -0.58
    conservancy
    -0.57
    senal
    -0.57
     recovering
    -0.56
     numbering
    -0.56
     successor
    -0.55
    luster
    -0.55
     restrooms
    -0.55
    POSITIVE LOGITS
    /_
    0.92
    /#
    0.84
    nw
    0.73
    cdn
    0.72
    /?
    0.69
    Ku
    0.67
    /-
    0.65
    mAh
    0.65
    000000
    0.64
    Ja
    0.63
    Act Density 0.014%

    No Known Activations