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

    Neuronpedia

    INDEX
    Explanations

    symbols or characters indicating the end of code structures or blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Len
    -0.15
    vas
    -0.15
     synonym
    -0.15
    ãĥ
    -0.14
    elligence
    -0.14
    öy
    -0.14
    Ñĥй
    -0.14
    ddb
    -0.14
    eteria
    -0.14
    inh
    -0.14
    POSITIVE LOGITS
    вад
    0.18
    atables
    0.17
    stem
    0.16
    ocker
    0.16
    iversite
    0.15
    ammer
    0.15
    ãĥĭãĥĥãĤ¯
    0.14
    672
    0.14
    aka
    0.14
     Gem
    0.14
    Act Density 0.001%

    No Known Activations