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

    Neuronpedia

    INDEX
    Explanations

    expressions related to approval or support, especially those using "thumb" or "thumbs up."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anz
    -0.17
    zel
    -0.16
    ag
    -0.15
    apo
    -0.15
     since
    -0.14
    oro
    -0.14
    agar
    -0.14
    WARN
    -0.14
     due
    -0.13
    Cent
    -0.13
    POSITIVE LOGITS
    że
    0.15
    ">ÃĹ</
    0.15
    еви
    0.15
    -pad
    0.14
    yt
    0.14
    raki
    0.14
    eck
    0.14
    cak
    0.14
     Pron
    0.14
    soever
    0.14
    Act Density 0.006%

    No Known Activations