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

    Neuronpedia

    INDEX
    Explanations

    recurring phrases that denote ranking or classification, particularly in music and entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     superf
    -0.70
     sewing
    -0.65
     leaflets
    -0.65
     ingredients
    -0.65
     detriment
    -0.64
     chem
    -0.64
     trooper
    -0.64
     dart
    -0.63
     laundry
    -0.63
     annexed
    -0.63
    POSITIVE LOGITS
    itialized
    1.10
    selves
    1.09
     Them
    0.98
     Him
    0.88
     Himself
    0.87
     Us
    0.86
    slaught
    0.84
    oret
    0.83
     Than
    0.80
     Course
    0.79
    Act Density 0.090%

    No Known Activations