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

    Neuronpedia

    INDEX
    Explanations

    themes related to evaluation and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ob
    -0.16
    ĮĢ
    -0.15
    ensi
    -0.15
    acher
    -0.15
    è«
    -0.15
    彦
    -0.14
    sted
    -0.14
    afen
    -0.14
    hv
    -0.13
    gam
    -0.13
    POSITIVE LOGITS
    Browsable
    0.16
    antro
    0.15
    baum
    0.15
    yme
    0.14
    #+
    0.14
    cth
    0.14
    //{{
    0.14
     اÙĦأس
    0.14
     than
    0.13
    anh
    0.13
    Act Density 0.254%

    No Known Activations