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

    Neuronpedia

    INDEX
    Explanations

    words related to personal strength, motivation, and priorities

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to priorities, motivations, and foundational elements of life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thinkable
    -0.82
    »Ĵ
    -0.67
    renches
    -0.63
    ghai
    -0.62
    orks
    -0.62
    amsung
    -0.62
    obos
    -0.60
    cair
    -0.60
     oneself
    -0.59
    ributed
    -0.58
    POSITIVE LOGITS
     asset
    0.78
     choice
    0.77
    aiden
    0.73
    Favorite
    0.72
     cousin
    0.71
     counterpart
    0.70
    choice
    0.70
    mate
    0.68
    iah
    0.68
     partner
    0.68
    Act Density 0.229%

    No Known Activations