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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or well-being

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

    happiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    olith
    -0.52
     useRef
    -0.49
     pith
    -0.47
    uride
    -0.46
    <!--
    -0.46
    }*/
    -0.44
     Golem
    -0.42
     dusk
    -0.42
     SUDOC
    -0.42
    scm
    -0.41
    POSITIVE LOGITS
    happy
    1.69
     HAPPY
    1.66
     happy
    1.66
    Happy
    1.66
     Happy
    1.63
    HAPPY
    1.53
     felices
    1.23
    happiness
    1.20
     feliz
    1.16
     happiest
    1.14
    Act Density 0.004%

    No Known Activations