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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to construction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to disjointed thoughts and cognitive disarray

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.59
    osate
    -0.55
    âķIJ
    -0.55
    ©¶æ
    -0.54
    æĺ
    -0.50
    ogether
    -0.50
    iak
    -0.50
    ;;;;;;;;;;;;
    -0.47
    awaru
    -0.47
    rison
    -0.47
    POSITIVE LOGITS
     overhead
    0.54
     infall
    0.49
     cis
    0.48
     blah
    0.48
     unch
    0.47
     drib
    0.46
     chores
    0.45
     shove
    0.44
     inev
    0.44
     darn
    0.43
    Act Density 3.640%

    No Known Activations