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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equivalents
    -0.14
    iro
    -0.14
    il
    -0.14
    rette
    -0.14
    ft
    -0.13
    ħn
    -0.13
     æ©
    -0.13
    rozen
    -0.13
     Nug
    -0.13
     prospects
    -0.13
    POSITIVE LOGITS
    BLEM
    0.14
     pretty
    0.14
    sis
    0.14
     odst
    0.14
    ãģĻ
    0.14
    inspace
    0.14
    ê°IJ
    0.14
    dorf
    0.13
    Pretty
    0.13
    mada
    0.13
    Act Density 0.078%

    No Known Activations