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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and criminal matters

    oai_token-act-pair · gpt-3.5-turbo

    topics related to relationships and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fitting
    -0.76
    taining
    -0.66
     Berm
    -0.65
     Glas
    -0.65
     Invention
    -0.64
     Speaking
    -0.63
    !:
    -0.63
     Brunswick
    -0.62
    rising
    -0.62
     Funding
    -0.61
    POSITIVE LOGITS
     lacks
    1.08
     contains
    1.07
     emits
    1.01
     suffers
    1.00
     cannot
    0.98
     possesses
    0.96
     fails
    0.96
     failed
    0.96
     lacked
    0.95
     had
    0.93
    Act Density 0.627%

    No Known Activations