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

    Neuronpedia

    INDEX
    Explanations

    references to "elektron" and various forms of the word "elephant."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    celed
    -0.20
    nbsp
    -0.16
    볬
    -0.16
    ecimal
    -0.15
    ipel
    -0.15
    meld
    -0.15
    scription
    -0.15
    rese
    -0.14
    £i
    -0.14
    IDEO
    -0.14
    POSITIVE LOGITS
    venth
    0.25
    uther
    0.24
    azar
    0.23
    phant
    0.21
    phants
    0.20
    uter
    0.17
    ÅŁt
    0.17
     Ele
    0.16
     ele
    0.16
     slack
    0.16
    Act Density 0.024%

    No Known Activations