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

    Neuronpedia

    INDEX
    Explanations

    structured data representations and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Recherches
    -0.74
    toDo
    -0.66
     Púb
    -0.65
     Micha
    -0.64
    \
    -0.63
    vertx
    -0.63
     rayons
    -0.62
     Diony
    -0.62
     umy
    -0.62
     \
    -0.61
    POSITIVE LOGITS
    ={{
    2.39
    {{
    1.55
     '{{
    1.54
     {{
    1.53
    ="{{
    1.51
    ">{{
    1.45
     "{{
    1.40
    [{{
    1.30
     ${{
    1.27
    >{{
    1.27
    Act Density 0.048%

    No Known Activations