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

    Neuronpedia

    INDEX
    Explanations

    phrases that express conditional statements or disclaimers regarding liability and warranties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olare
    -0.16
    adv
    -0.15
    egra
    -0.15
     Kis
    -0.15
     Kiss
    -0.15
    æ´ŀ
    -0.15
    isas
    -0.14
    gov
    -0.14
    ÑıÑģ
    -0.14
    خاÙĨ
    -0.14
    POSITIVE LOGITS
    zcze
    0.18
    zzo
    0.17
    inati
    0.16
    psilon
    0.15
    abbo
    0.15
     Dmit
    0.15
    avian
    0.14
     Duffy
    0.14
    rin
    0.14
    nal
    0.14
    Act Density 0.005%

    No Known Activations