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

    Neuronpedia

    INDEX
    Explanations

    descriptions of actions involving driving or travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancell
    -0.15
    deniz
    -0.14
    ianne
    -0.14
    QUIRE
    -0.14
    uve
    -0.14
    irable
    -0.14
    eum
    -0.14
    é¢ij次
    -0.14
    mlin
    -0.13
    uye
    -0.13
    POSITIVE LOGITS
     innoc
    0.22
     routine
    0.20
    æŃ£å¸¸
    0.19
     innocent
    0.18
     normal
    0.17
     returning
    0.17
     nearby
    0.17
    routine
    0.17
     harmless
    0.16
     peacefully
    0.16
    Act Density 0.096%

    No Known Activations