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

    Neuronpedia

    INDEX
    Explanations

    descriptors related to physical traits and emotions

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

    ending in "-minded", "-hearted", "-headed", "-tempered", or "-spoken"

    np_acts-logits-general · gemini-2.0-flash

    character adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.68
     AssemblyCompany
    -0.60
    könig
    -0.59
    alue
    -0.59
    Cyfeiriadau
    -0.59
    IUrlHelper
    -0.58
     kasarigan
    -0.55
    räck
    -0.53
    ständ
    -0.52
    日閲覧
    -0.52
    POSITIVE LOGITS
     minded
    1.02
    minded
    0.89
    hearted
    0.83
     hearted
    0.82
    headed
    0.75
     headed
    0.75
    mindedness
    0.73
    eyed
    0.71
     eyed
    0.70
     tempered
    0.69
    Act Density 0.219%

    No Known Activations