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

    Neuronpedia

    INDEX
    Explanations

    references to coercive or forceful actions

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

    acting with force or compulsion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <=",
    -0.50
     zéro
    -0.49
    principalTable
    -0.48
    Географи
    -0.48
     sogni
    -0.48
     Privacidade
    -0.46
    abá
    -0.45
    abetes
    -0.44
    awakeFromNib
    -0.44
    estacks
    -0.44
    POSITIVE LOGITS
     forcefully
    1.59
     forcibly
    1.53
     forcible
    1.33
     forceful
    1.27
    cibly
    1.06
     violently
    0.81
     Force
    0.71
    强行
    0.68
    Force
    0.67
    force
    0.66
    Act Density 0.005%

    No Known Activations