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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating freedom and permissiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with freedom or being unrestrained

    np_acts-logits-general · gemini-2.0-flash

    unhindered movement and freedom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.78
     Exacts
    -0.64
    地味
    -0.55
    msgTypes
    -0.53
    makeText
    -0.53
    日閲覧
    -0.52
     <>",
    -0.52
     تكبرها
    -0.52
    agraph
    -0.52
     digno
    -0.51
    POSITIVE LOGITS
     freely
    1.63
     freedom
    1.58
     free
    1.57
     unrestricted
    1.46
     freer
    1.37
     bebas
    1.37
    自由
    1.35
    freedom
    1.34
     loose
    1.33
     libre
    1.32
    Act Density 0.471%

    No Known Activations