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

    Neuronpedia

    INDEX
    Explanations

    words related to repurposing or reusing objects for a different purpose

    oai_token-act-pair · gpt-3.5-turbo

    words related to "pose" or "posing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essional
    -0.79
    haw
    -0.71
    hips
    -0.68
     whisk
    -0.66
    aeus
    -0.65
    externalActionCode
    -0.63
    win
    -0.62
    ingham
    -0.61
    batch
    -0.61
    BIT
    -0.60
    POSITIVE LOGITS
    xual
    1.27
    pose
    1.27
    posed
    1.16
    posing
    1.07
    poses
    1.04
    itives
    1.02
    mble
    0.83
    zhen
    0.76
     rall
    0.73
    idon
    0.71
    Act Density 0.010%

    No Known Activations