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

    Neuronpedia

    INDEX
    Explanations

    concepts related to global education and community service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Apparently
    -0.69
     apparently
    -0.60
     pretty
    -0.59
     Apparently
    -0.59
    (?)
    -0.58
     vaguely
    -0.58
     strangely
    -0.57
     probably
    -0.56
     (!)
    -0.54
     recently
    -0.53
    POSITIVE LOGITS
     themſelves
    0.86
     itſelf
    0.84
     throughout
    0.83
    throughout
    0.81
     across
    0.81
     whoſe
    0.76
     attraverso
    0.76
     poprzez
    0.75
     againſt
    0.74
    across
    0.73
    Act Density 0.540%

    No Known Activations