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

    Neuronpedia

    INDEX
    Explanations

    possessive forms indicating ownership or association

    oai_token-act-pair · gpt-3.5-turbo

    references to personal attributes and characteristics of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mir
    -0.86
    tackle
    -0.79
    ernels
    -0.76
    quished
    -0.74
    etsk
    -0.71
    unic
    -0.70
    mire
    -0.69
    cro
    -0.69
    odon
    -0.68
    asus
    -0.67
    POSITIVE LOGITS
     intentions
    1.28
     nationality
    1.25
     ethnicity
    1.22
     own
    1.20
     ability
    1.16
     preferences
    1.15
     qualifications
    1.15
     willingness
    1.13
     age
    1.11
     abilities
    1.10
    Act Density 0.232%

    No Known Activations