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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the mind or mental processes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "minds" and related mental processes or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ér
    -0.67
    y
    -0.64
    ier
    -0.62
    ée
    -0.62
    ................................
    -0.61
    que
    -0.61
    qq
    -0.60
    aro
    -0.59
     https
    -0.58
    wind
    -0.58
    POSITIVE LOGITS
     minds
    4.24
     mind
    2.27
     hearts
    1.96
     brains
    1.90
    mind
    1.88
     souls
    1.87
     Mind
    1.65
    Mind
    1.58
     mouths
    1.54
     throats
    1.44
    Act Density 0.011%

    No Known Activations