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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical events or stories

    oai_token-act-pair · gpt-3.5-turbo

    conversations about feelings of regret or reflection on past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undrum
    -0.55
    currently
    -0.54
    eport
    -0.54
     follows
    -0.51
     reiterate
    -0.51
    ierra
    -0.51
     complicate
    -0.50
    veland
    -0.49
    orio
    -0.49
    iquid
    -0.49
    POSITIVE LOGITS
     beforehand
    0.78
     earlier
    0.69
     yesterday
    0.67
     previous
    0.65
     last
    0.64
     theirs
    0.56
     prior
    0.56
    terday
    0.55
     originally
    0.54
    addafi
    0.54
    Act Density 2.673%

    No Known Activations