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

    Neuronpedia

    INDEX
    Explanations

    references to law and governance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arsing
    -0.16
    æ´¥
    -0.16
     tentative
    -0.16
    á»ij
    -0.15
    _priv
    -0.14
    忽
    -0.13
     æļ
    -0.13
    athi
    -0.13
     almost
    -0.13
    398
    -0.13
    POSITIVE LOGITS
     shoulder
    0.24
     firm
    0.22
    èĤ©
    0.20
     плеÑĩ
    0.20
     Firm
    0.20
     frat
    0.19
     Shoulder
    0.18
    firm
    0.18
     consolid
    0.17
     solid
    0.16
    Act Density 0.085%

    No Known Activations