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

    Neuronpedia

    INDEX
    Explanations

    references to goals or objectives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sets objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OOTDTY
    -0.55
     Dinamarca
    -0.51
     inoxydable
    -0.51
    <bos>
    -0.50
     Otras
    -0.48
     жив
    -0.47
    ForRow
    -0.47
    깐
    -0.47
     Rosas
    -0.47
    import
    -0.47
    POSITIVE LOGITS
     objectives
    1.83
     Objectives
    1.77
    Objectives
    1.59
    objectives
    1.59
     OBJECTIVES
    1.44
     objectifs
    1.20
    OBJECTIVES
    1.08
     objetivos
    1.06
     goals
    1.05
     Goals
    1.00
    Act Density 0.004%

    No Known Activations