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

    Neuronpedia

    INDEX
    Explanations

    statements indicating approval or disapproval

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culus
    -0.77
    ukemia
    -0.74
    culosis
    -0.70
    aido
    -0.69
    miah
    -0.65
    adelphia
    -0.65
    ÃŃa
    -0.64
    raviolet
    -0.64
    vation
    -0.63
    odcast
    -0.62
    POSITIVE LOGITS
     therefore
    1.16
     consequently
    1.11
     accordingly
    0.94
     deserve
    0.86
    ":"/
    0.78
     contribute
    0.76
     deserving
    0.74
     deserves
    0.72
    should
    0.71
     alike
    0.71
    Act Density 0.381%

    No Known Activations