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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating proximity or upcoming events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otland
    -0.17
    bable
    -0.17
    ÙĪد
    -0.15
    ://'
    -0.15
    hiba
    -0.15
    éĽ
    -0.14
    паÑĤ
    -0.14
    еÑĢÑĥ
    -0.14
    æ£ļ
    -0.14
    inals
    -0.14
    POSITIVE LOGITS
    951
    0.16
    oom
    0.16
     corner
    0.15
     Human
    0.15
     penc
    0.14
    aea
    0.14
    441
    0.14
     Burn
    0.14
     burn
    0.14
    merc
    0.14
    Act Density 0.005%

    No Known Activations