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

    Neuronpedia

    INDEX
    Explanations

    relationships and dynamics among characters in a narrative

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

    characters like Amber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.51
    expandindo
    -0.41
     méri
    -0.40
    Personensuche
    -0.39
    tatuajes
    -0.38
    这份
    -0.38
     zví
    -0.38
    อร่อย
    -0.38
    translator
    -0.37
     ouder
    -0.37
    POSITIVE LOGITS
    patine
    0.47
    SBATCH
    0.44
     cruel
    0.42
     evil
    0.41
    GenerationType
    0.40
    omock
    0.40
     pompous
    0.39
     arrogant
    0.39
    getSystemService
    0.39
     worst
    0.39
    Act Density 0.059%

    No Known Activations