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

    Neuronpedia

    INDEX
    Explanations

    phrases related to following or imitating someone's actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    references to "footsteps" and "steps"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iser
    -0.89
    izations
    -0.75
    nia
    -0.74
    izer
    -0.72
    fy
    -0.70
    binary
    -0.69
    ombat
    -0.69
    iza
    -0.66
    ohyd
    -0.66
    rw
    -0.65
    POSITIVE LOGITS
     footsteps
    1.37
    steps
    1.11
    prints
    0.94
    print
    0.84
     footprints
    0.80
     echoing
    0.79
    dale
    0.73
    DragonMagazine
    0.73
     echoed
    0.70
     Steps
    0.69
    Act Density 0.015%

    No Known Activations