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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icros
    -0.18
    zoek
    -0.16
    cent
    -0.15
    au
    -0.14
    опаÑģ
    -0.14
    antro
    -0.14
    rade
    -0.14
    posables
    -0.14
    lifting
    -0.13
    ï¿¥
    -0.13
    POSITIVE LOGITS
    webkit
    0.19
    571
    0.18
    =-=-=-=-=-=-=-=-
    0.17
    anko
    0.16
     بÙĪابة
    0.16
     ðŁij
    0.15
    Argb
    0.15
     âĹĦ
    0.15
     Redistributions
    0.15
    ëĬIJ
    0.15
    Act Density 0.095%

    No Known Activations