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

    Neuronpedia

    INDEX
    Explanations

    verbs related to personal drive and determination

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to motivation and motivational factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esan
    -0.75
    rock
    -0.71
    maid
    -0.71
    opy
    -0.67
    rooms
    -0.67
    hold
    -0.66
    iannopoulos
    -0.66
    semble
    -0.64
    tower
    -0.63
    opic
    -0.63
    POSITIVE LOGITS
    ivated
    1.10
    ivation
    0.90
     motivate
    0.86
     motivation
    0.85
     cooker
    0.79
    ivating
    0.79
     motivated
    0.76
    ="#
    0.74
     compel
    0.73
     compelled
    0.73
    Act Density 0.014%

    No Known Activations