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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe movement from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating possession or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":[
    -0.76
    ategory
    -0.76
     [];
    -0.73
    cephal
    -0.70
    icio
    -0.68
    verage
    -0.67
    otin
    -0.67
    abetic
    -0.65
    alogue
    -0.65
    groups
    -0.64
    POSITIVE LOGITS
     displeasure
    1.10
     way
    1.10
     debut
    1.06
     mark
    1.04
     own
    1.01
     rounds
    0.99
     intentions
    0.94
     fortune
    0.89
     presence
    0.89
     voices
    0.87
    Act Density 0.046%

    No Known Activations