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

    Neuronpedia

    INDEX
    Explanations

    phrases related to goals or objectives

    oai_token-act-pair · gpt-3.5-turbo

    statements of intention or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.80
    Usage
    -0.77
    Pass
    -0.72
    士
    -0.70
    Rare
    -0.66
    Uncommon
    -0.64
    Newsletter
    -0.63
    Person
    -0.63
    Iss
    -0.62
     Sapp
    -0.62
    POSITIVE LOGITS
    emouth
    0.90
    lessly
    0.88
    ims
    0.79
     aims
    0.78
    sonian
    0.78
    ģĸ
    0.77
     aim
    0.75
    omething
    0.75
    irection
    0.74
    yip
    0.74
    Act Density 0.015%

    No Known Activations