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

    Neuronpedia

    INDEX
    Explanations

    terms related to cyber attacks and misinformation tactics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Autorizaciones
    -0.41
     ospiti
    -0.41
     avoient
    -0.40
    sizeCache
    -0.40
    デューサー
    -0.39
     betreft
    -0.39
     Vereine
    -0.37
     towarzys
    -0.37
     escritora
    -0.36
     illustrazione
    -0.36
    POSITIVE LOGITS
     sabotage
    0.67
     Sabo
    0.58
    poison
    0.54
     sabo
    0.53
     prank
    0.53
     deliberately
    0.51
    故意
    0.50
     poison
    0.49
     pranks
    0.48
    わざ
    0.48
    Act Density 0.499%

    No Known Activations