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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating enjoyment and caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astos
    -0.16
    teri
    -0.15
    itizen
    -0.15
    .entries
    -0.15
    ãĥªãĥ¼ãĤº
    -0.14
    rop
    -0.14
     Terry
    -0.14
    ãģ°ãģĭãĤĬ
    -0.14
    orgen
    -0.13
     дов
    -0.13
    POSITIVE LOGITS
    atu
    0.17
    ogo
    0.15
    omite
    0.15
    atz
    0.15
    izzo
    0.14
    LEN
    0.14
    çe
    0.14
    çķ¥
    0.14
    /stdc
    0.14
     accordingly
    0.14
    Act Density 0.129%

    No Known Activations