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

    Neuronpedia

    INDEX
    Explanations

    incidents of violence or crime

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.73
    hichever
    -0.62
    romolecules
    -0.60
     dAtA
    -0.55
     virtual
    -0.53
    Hozzáférés
    -0.52
    Wherever
    -0.52
     Савезне
    -0.52
    asties
    -0.52
     prettiest
    -0.52
    POSITIVE LOGITS
     near
    0.93
     allegedly
    0.81
    near
    0.80
     early
    0.71
     shortly
    0.71
     неда
    0.69
     outside
    0.69
     believed
    0.69
     diduga
    0.67
    Investigators
    0.67
    Act Density 0.422%

    No Known Activations