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

    Neuronpedia

    INDEX
    Explanations

    concepts related to power dynamics and victimization in social contexts

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

    surrounding "victim" or "victims"

    np_acts-logits-general · gemini-2.0-flash

    innocent victim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.79
    tagext
    -0.74
    EnumMember
    -0.67
    ніципалі
    -0.66
    География
    -0.64
    Kjelder
    -0.63
    Skocz
    -0.60
    EDEFAULT
    -0.60
    RegistryLite
    -0.58
    ₂+
    -0.57
    POSITIVE LOGITS
     victims
    1.82
     victim
    1.76
     victimes
    1.52
     Victims
    1.50
    victim
    1.47
     victime
    1.44
     Victim
    1.39
     víctima
    1.39
    受害
    1.37
    Victim
    1.32
    Act Density 0.420%

    No Known Activations