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

    Neuronpedia

    INDEX
    Explanations

    phrases mentioning a group of people working together

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people working or collaborating together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.64
    BN
    -0.64
     ERA
    -0.64
    cing
    -0.61
    Tri
    -0.61
     Spokane
    -0.61
     iT
    -0.60
    032
    -0.59
    ARB
    -0.59
     RIS
    -0.58
    POSITIVE LOGITS
     alike
    0.95
     respectively
    0.84
    hots
    0.77
     descended
    0.72
    axter
    0.72
     erected
    0.68
     succeeded
    0.67
    hesda
    0.67
     accompanying
    0.67
    utterstock
    0.66
    Act Density 0.147%

    No Known Activations