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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data and technology-driven concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to motivations or factors driving actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interchange
    -0.74
     enlist
    -0.70
     Pearce
    -0.67
     iv
    -0.67
     gym
    -0.67
     cease
    -0.66
     memorial
    -0.66
     wonder
    -0.65
     Ul
    -0.65
     allot
    -0.64
    POSITIVE LOGITS
    driven
    3.16
    drive
    1.53
    Dri
    1.48
    flow
    1.29
    mot
    1.24
    dri
    1.24
    driving
    1.24
    loading
    1.23
    Drive
    1.09
     Dri
    1.05
    Act Density 0.025%

    No Known Activations