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

    Neuronpedia

    INDEX
    Explanations

    elements of user engagement and relatable experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ught
    -0.15
    /stdc
    -0.15
    ÑĢÑĸÑĩ
    -0.15
    okies
    -0.14
    hm
    -0.14
    ozy
    -0.14
    entes
    -0.13
    ='".$_
    -0.13
    ozor
    -0.13
    eree
    -0.13
    POSITIVE LOGITS
     never
    1.28
    never
    1.13
     Never
    1.09
    Never
    1.05
     NEVER
    1.02
     nunca
    0.96
     никогда
    0.85
     jamais
    0.77
     nikdy
    0.72
     нÑĸколи
    0.60
    Act Density 0.448%

    No Known Activations