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

    Neuronpedia

    INDEX
    Explanations

    phrases related to affordability and socioeconomic status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    610
    -0.15
    agency
    -0.15
    hti
    -0.14
    ([{
    -0.14
     Attention
    -0.14
     Architect
    -0.14
    abis
    -0.14
     Arcade
    -0.13
    ancestor
    -0.13
    akov
    -0.13
    POSITIVE LOGITS
     aff
    0.89
     Aff
    0.85
    aff
    0.84
    Aff
    0.79
     AFF
    0.75
    -aff
    0.73
    _aff
    0.66
    'aff
    0.65
    AFF
    0.63
     afford
    0.63
    Act Density 0.090%

    No Known Activations