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

    Neuronpedia

    INDEX
    Explanations

    preferences and choices, particularly regarding technology and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emig
    -0.62
     Aspir
    -0.60
    dbo
    -0.60
    addCriterion
    -0.59
     Compet
    -0.59
     Summon
    -0.59
     Immig
    -0.58
     Fusion
    -0.57
     Geometry
    -0.56
     Geo
    -0.56
    POSITIVE LOGITS
     Realität
    0.51
     Menschheit
    0.47
     jueces
    0.46
    Autoritní
    0.46
     preferencias
    0.45
     preferencia
    0.45
     derived
    0.44
     prefer
    0.44
     prefier
    0.43
     naciones
    0.43
    Act Density 0.219%

    No Known Activations