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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or contentment

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

    happy and unhappy sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     useRef
    -0.47
    scm
    -0.42
    olith
    -0.41
    sc
    -0.39
     Prism
    -0.38
    یں
    -0.38
    ci
    -0.38
     pith
    -0.38
    <!--
    -0.37
     "]
    -0.37
    POSITIVE LOGITS
    Happy
    0.99
     HAPPY
    0.98
    HAPPY
    0.97
    happy
    0.96
     Happy
    0.94
     happy
    0.83
    happiness
    0.83
    Happiness
    0.82
     felices
    0.76
     Happiness
    0.76
    Act Density 0.008%

    No Known Activations