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

    Neuronpedia

    INDEX
    Explanations

    references to military ranks or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŀ
    -2.85
    ¬
    -2.50
    ĺ
    -2.45
    ĵ
    -2.43
    ĥ½
    -2.29
    Ĵ
    -2.24
    Ŀ
    -2.20
    Ļ
    -2.20
    ĸ
    -2.19
    ģ
    -2.18
    POSITIVE LOGITS
    liness
    2.26
    ships
    1.97
    abbit
    1.81
    glut
    1.79
    ly
    1.78
    ily
    1.77
    zzle
    1.75
    intendent
    1.72
    theless
    1.71
    ship
    1.70
    Act Density 0.080%

    No Known Activations