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

    Neuronpedia

    INDEX
    Explanations

    phrases related to educational activities and instructions

    oai_token-act-pair · gpt-3.5-turbo

    activities related to education and personal development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hap
    -0.71
    cci
    -0.68
    ACTED
    -0.68
    eus
    -0.68
    ixed
    -0.68
    atron
    -0.67
    Ô
    -0.67
    idas
    -0.67
    xus
    -0.66
    ère
    -0.66
    POSITIVE LOGITS
     habits
    0.98
     ability
    0.93
     prowess
    0.89
     behaviour
    0.86
     cessation
    0.85
     spree
    0.85
     behaviours
    0.84
     capability
    0.81
     behavior
    0.81
     behaviors
    0.81
    Act Density 0.247%

    No Known Activations