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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ans
    -0.17
    anton
    -0.16
    noon
    -0.16
    ander
    -0.15
    uv
    -0.15
    p
    -0.15
    enberg
    -0.15
    imo
    -0.14
    ò
    -0.14
     beg
    -0.14
    POSITIVE LOGITS
    PEAT
    0.18
    ãģıãĤĵ
    0.16
    loquent
    0.15
     steroids
    0.15
    -valu
    0.15
    ocz
    0.15
    istrovstvÃŃ
    0.14
    purpose
    0.14
    zÃŃ
    0.14
    datagrid
    0.14
    Act Density 0.186%

    No Known Activations