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

    Neuronpedia

    INDEX
    Explanations

    words related to indulgence and self-gratification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eus
    -0.17
     Gro
    -0.16
    eks
    -0.16
    eko
    -0.16
    ÙĪع
    -0.15
    رÙĪØ´
    -0.15
    zza
    -0.14
    erness
    -0.14
    %M
    -0.14
    quat
    -0.14
    POSITIVE LOGITS
    ging
    0.60
    ged
    0.58
    ges
    0.54
    ger
    0.46
    gers
    0.44
    ge
    0.40
    gem
    0.39
    GING
    0.36
    g
    0.35
    GE
    0.35
    Act Density 0.022%

    No Known Activations