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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following or imitating someone's actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases about following or being influenced by others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rencies
    -0.71
    bable
    -0.69
    bart
    -0.65
    igned
    -0.65
    idium
    -0.64
    女
    -0.64
    mpeg
    -0.62
    usting
    -0.60
    ividual
    -0.59
    Duration
    -0.58
    POSITIVE LOGITS
     tradition
    0.93
     previous
    0.86
     predecessor
    0.82
     predecessors
    0.82
    era
    0.78
     footsteps
    0.76
     prev
    0.75
     vein
    0.74
     traditional
    0.71
     traditions
    0.71
    Act Density 0.185%

    No Known Activations