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

    Neuronpedia

    INDEX
    Explanations

    verbs related to motivation and actions that drive individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to motivation and what drives people to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.82
    maid
    -0.74
    rooms
    -0.73
    hold
    -0.72
    aird
    -0.70
    semble
    -0.68
     Leopard
    -0.68
     Canad
    -0.67
    iannopoulos
    -0.67
    erial
    -0.66
    POSITIVE LOGITS
    ivated
    0.99
     motivation
    0.95
    ivation
    0.89
     motivate
    0.83
     cooker
    0.80
     motivations
    0.78
     motivating
    0.76
     motivated
    0.75
     compel
    0.74
     compelled
    0.74
    Act Density 0.035%

    No Known Activations