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

    Neuronpedia

    INDEX
    Explanations

    references to deception or hoaxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.16
    core
    -0.16
    'ın
    -0.15
    amoto
    -0.15
    nels
    -0.14
    rik
    -0.14
     wholly
    -0.14
    rost
    -0.14
    ially
    -0.14
    ucci
    -0.14
    POSITIVE LOGITS
    ÌĪ
    0.19
    yssey
    0.18
    readcr
    0.17
    ìį¨
    0.17
    theast
    0.17
    xygen
    0.17
    ys
    0.16
     pháºŃn
    0.16
    ãĤ©
    0.15
     Angeles
    0.15
    Act Density 0.489%

    No Known Activations