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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical records or documentation

    oai_token-act-pair · gpt-3.5-turbo

    extensive use of punctuation and conjunctions within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vier
    -0.82
    auri
    -0.82
    enth
    -0.80
    rake
    -0.74
    isp
    -0.73
    oor
    -0.73
    culus
    -0.73
    avan
    -0.71
    azard
    -0.70
    anche
    -0.69
    POSITIVE LOGITS
     counterparts
    0.92
     namesake
    0.83
     brethren
    0.79
     selves
    0.77
     sensibilities
    0.75
     hometown
    0.72
     counterpart
    0.71
     holdings
    0.70
    æ©Ł
    0.70
     qualities
    0.70
    Act Density 0.838%

    No Known Activations