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

    Neuronpedia

    INDEX
    Explanations

    filesystem and directory structure references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acci
    -0.66
     plague
    -0.65
     Guarant
    -0.62
     Gap
    -0.60
     Watkins
    -0.59
     additive
    -0.57
     impro
    -0.55
     Airways
    -0.54
     advance
    -0.53
     sil
    -0.52
    POSITIVE LOGITS
    /,
    1.04
    /.
    1.01
    ascript
    0.90
     directory
    0.87
    dir
    0.87
    \
    0.84
    /_
    0.84
    \/
    0.83
    /$
    0.82
    ãĥ´ãĤ¡
    0.82
    Act Density 0.052%

    No Known Activations