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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being in a position of authority or responsibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to authority or leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -0.86
     pse
    -0.83
    icz
    -0.79
     livest
    -0.76
     normalized
    -0.72
     bom
    -0.67
    igsaw
    -0.67
    orph
    -0.67
    anmar
    -0.65
     Birth
    -0.65
    POSITIVE LOGITS
    heet
    0.82
    abilities
    0.81
    AGES
    0.80
    charges
    0.80
     charge
    0.79
    boards
    0.79
    Charges
    0.79
     charges
    0.79
    eters
    0.78
    backs
    0.78
    Act Density 0.022%

    No Known Activations