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

    Neuronpedia

    INDEX
    Explanations

    aspirational statements and goals

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

    "goal" or "goals" (variations and context)

    np_acts-logits-general · gemini-2.0-flash

    goals and objectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abetta
    -0.59
    manuelle
    -0.57
    layah
    -0.48
    ệ
    -0.47
     विश्वसनीयता
    -0.47
    hdys
    -0.46
     correlation
    -0.46
     tec
    -0.45
    ですよ
    -0.44
     regla
    -0.44
    POSITIVE LOGITS
     goals
    1.69
     Goals
    1.48
    goals
    1.45
     goal
    1.44
    Goals
    1.41
     objectives
    1.38
     GOALS
    1.38
     aims
    1.33
    goal
    1.33
     Goal
    1.25
    Act Density 0.336%

    No Known Activations