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

    Neuronpedia

    INDEX
    Explanations

    conditions or actions related to physical objects or body parts, such as temperature, healing, growth, and the "not" negation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to maintaining stability and functionality in various systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vows
    -0.80
     Families
    -0.77
    antine
    -0.70
     acron
    -0.68
     affidav
    -0.66
     chiefs
    -0.66
     titles
    -0.66
     weddings
    -0.65
     campaigns
    -0.65
     anecdotes
    -0.65
    POSITIVE LOGITS
     oxid
    0.81
     itself
    0.77
     hardness
    0.75
     vibr
    0.74
    absor
    0.74
     unus
    0.73
     usable
    0.72
     protr
    0.72
     rotated
    0.71
     orbit
    0.69
    Act Density 0.613%

    No Known Activations