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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sharing or distributing a portion of something

    oai_token-act-pair · gpt-3.5-turbo

    references to parts or portions of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    verbs
    -0.67
     Parade
    -0.62
    urat
    -0.59
    Recomm
    -0.57
    Fight
    -0.53
     Trop
    -0.53
     grandmother
    -0.52
     commissions
    -0.52
     conditions
    -0.52
    MJ
    -0.51
    POSITIVE LOGITS
     thereof
    1.20
     of
    0.94
    icularly
    0.87
    atical
    0.78
    eenth
    0.77
    nown
    0.77
    ately
    0.74
    eki
    0.74
    ners
    0.74
    ate
    0.72
    Act Density 0.082%

    No Known Activations