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

    Neuronpedia

    INDEX
    Explanations

    phrases related to descriptions of creative works or artistic productions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.81
    rius
    -0.81
    itational
    -0.77
    orem
    -0.77
    ource
    -0.73
    ulla
    -0.72
    eln
    -0.72
     Moines
    -0.72
    erent
    -0.72
    topic
    -0.71
    POSITIVE LOGITS
     culminating
    1.16
     albeit
    1.11
     indistinguishable
    1.08
     morp
    1.06
     devoid
    1.03
     echoing
    1.02
     reminding
    1.00
     embod
    0.98
     oblivious
    0.97
     drowning
    0.96
    Act Density 0.355%

    No Known Activations