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

    Neuronpedia

    INDEX
    Explanations

    words related to obstacles or hindrances

    oai_token-act-pair · gpt-3.5-turbo

    references to obstacles or hindrances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivery
    -0.80
    EVA
    -0.73
    ership
    -0.73
    phis
    -0.72
     largeDownload
    -0.72
    iability
    -0.70
    orable
    -0.68
    ories
    -0.68
    ergy
    -0.66
    sch
    -0.66
    POSITIVE LOGITS
     barriers
    1.38
     barrier
    1.22
     walls
    0.89
     Barrier
    0.88
     obstacles
    0.85
     wall
    0.82
    riers
    0.82
    buster
    0.81
     separating
    0.80
     Walls
    0.79
    Act Density 0.007%

    No Known Activations