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

    Neuronpedia

    INDEX
    Explanations

    terms related to data analysis and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ£
    -0.17
    tuk
    -0.15
    ãĥĭãĥ¥
    -0.14
    roman
    -0.14
    .alt
    -0.14
    аниÑĨ
    -0.14
    _MAGIC
    -0.14
     Zimmerman
    -0.14
     GOODMAN
    -0.14
    oret
    -0.13
    POSITIVE LOGITS
    cura
    0.15
     kola
    0.15
    ìĽħ
    0.15
    rees
    0.15
    rica
    0.14
    enia
    0.14
    ussion
    0.14
    zilla
    0.14
     ull
    0.14
     cul
    0.13
    Act Density 0.001%

    No Known Activations