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

    Neuronpedia

    INDEX
    Explanations

    verbs and adjectives related to information dissemination or management

    oai_token-act-pair · gpt-3.5-turbo

    past participle verbs and phrases indicating status or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LOT
    -0.68
    ggles
    -0.60
    itton
    -0.60
     assorted
    -0.55
    Ru
    -0.53
     Dimension
    -0.52
     humble
    -0.52
     Dragons
    -0.51
     passages
    -0.51
    Zone
    -0.51
    POSITIVE LOGITS
     anymore
    1.63
     nor
    1.47
     anywhere
    1.03
     whatsoever
    0.97
     necessarily
    0.96
    yet
    0.95
     properly
    0.87
     slightest
    0.86
    achable
    0.85
     yet
    0.84
    Act Density 0.186%

    No Known Activations