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

    Neuronpedia

    INDEX
    Explanations

    words related to loss or decline

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UNCH
    -0.81
    IVERS
    -0.79
     Aware
    -0.76
    é¾
    -0.76
    Cu
    -0.75
    SPONSORED
    -0.70
    Stre
    -0.70
    Merc
    -0.69
     Enhancement
    -0.69
    Champ
    -0.67
    POSITIVE LOGITS
     own
    1.34
     footing
    0.99
     grip
    0.95
     virginity
    0.93
     customary
    0.93
     belongings
    0.93
     bearings
    0.92
     knees
    0.90
     usual
    0.89
     grasp
    0.89
    Act Density 0.174%

    No Known Activations