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

    Neuronpedia

    INDEX
    Explanations

    words associated with violence and intense emotions

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

    killing, brutal, hurt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.59
     Italijani
    -0.53
    ंदीखरीदारी
    -0.50
     يتيمه
    -0.49
     informée
    -0.49
    findpost
    -0.49
     houſe
    -0.48
    ceğine
    -0.47
     ligiloj
    -0.46
    ſelf
    -0.45
    POSITIVE LOGITS
    Harsh
    0.44
     devastating
    0.42
     Killed
    0.41
     keenly
    0.41
     duro
    0.41
     Harsh
    0.40
     ağır
    0.39
     élimin
    0.39
    Killed
    0.38
     excruciating
    0.38
    Act Density 0.044%

    No Known Activations