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

    Neuronpedia

    INDEX
    Explanations

    verbs related to exerting control or influence over others

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "force" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nings
    -0.79
    mbuds
    -0.78
    nown
    -0.73
    vironment
    -0.72
    issance
    -0.72
    thus
    -0.71
     æľ
    -0.68
    amac
    -0.68
    ernels
    -0.68
    available
    -0.67
    POSITIVE LOGITS
     concessions
    0.86
     overtime
    0.85
     closure
    0.83
     conversions
    0.81
     entry
    0.80
     confessions
    0.80
     laborers
    0.79
     compliance
    0.79
     obedience
    0.77
    otom
    0.76
    Act Density 0.066%

    No Known Activations