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

    Neuronpedia

    INDEX
    Explanations

    terms related to intention, purpose, and selection in various contexts

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

    purposeful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.50
     Inſ
    -0.44
     Reſ
    -0.42
     automatiques
    -0.39
    Tikang
    -0.38
     curé
    -0.38
     avoient
    -0.38
     Conſ
    -0.38
     mécanisme
    -0.38
     Monfieur
    -0.37
    POSITIVE LOGITS
     purposeful
    0.92
     purposefully
    0.73
    built
    0.73
    purpose
    0.68
     purpose
    0.66
     Purpose
    0.65
     purposely
    0.65
     purpo
    0.59
     PURPOSE
    0.59
    Purpose
    0.57
    Act Density 0.005%

    No Known Activations