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

    Neuronpedia

    INDEX
    Explanations

    content related to crime and punishment in socio-political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.60
     gynhyrchwyd
    -0.59
    GEBURTS
    -0.59
     avoient
    -0.58
     myſelf
    -0.57
     feroit
    -0.56
     Perſ
    -0.53
     houſe
    -0.52
    balleur
    -0.52
    verwijspagina
    -0.52
    POSITIVE LOGITS
     compares
    0.44
     worst
    0.40
     worse
    0.39
     kı
    0.39
    序
    0.38
     compared
    0.37
     signaling
    0.36
    比
    0.35
     ob
    0.34
     compar
    0.34
    Act Density 0.147%

    No Known Activations