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

    Neuronpedia

    INDEX
    Explanations

    dialogues and conversational exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĺĵ
    -0.15
    ino
    -0.15
    емо
    -0.15
    linger
    -0.14
    lifting
    -0.14
    ault
    -0.14
    ãĥ¼ãĥĸãĥ«
    -0.14
     unseen
    -0.14
    é§
    -0.14
    º
    -0.14
    POSITIVE LOGITS
     simply
    0.31
     crypt
    0.28
     simplement
    0.27
     merely
    0.25
     vague
    0.25
     nothing
    0.23
    crypt
    0.22
     only
    0.22
    Simply
    0.20
     neither
    0.20
    Act Density 0.207%

    No Known Activations