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

    Neuronpedia

    INDEX
    Explanations

    references to truth and the concept of truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.15
    oo
    -0.14
    list
    -0.14
    PLAN
    -0.14
    apia
    -0.14
    erno
    -0.14
    ita
    -0.14
    utton
    -0.14
    Edition
    -0.14
    igan
    -0.13
    POSITIVE LOGITS
    fully
    0.27
    fulness
    0.22
    /false
    0.19
    .djangoproject
    0.18
    ãģªãĤĭ
    0.17
    ylene
    0.16
    flen
    0.16
    enticator
    0.15
    soever
    0.15
    yntax
    0.15
    Act Density 0.035%

    No Known Activations