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

    Neuronpedia

    INDEX
    Explanations

    questions and prompts that encourage reflection and action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.76
    LookAnd
    -0.66
     nakalista
    -0.62
    ddots
    -0.60
     فريبيس
    -0.59
    AutoScale
    -0.59
    FormTagHelper
    -0.59
    herself
    -0.58
    -0.57
     држа
    -0.56
    POSITIVE LOGITS
    ranton
    0.58
     Theſe
    0.56
    )";
    0.55
    {§
    0.55
     poffible
    0.54
     uſe
    0.54
     Helium
    0.53
     prisonniers
    0.53
     theſe
    0.52
     ettei
    0.52
    Act Density 0.321%

    No Known Activations