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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote relationships and memories associated with people or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.08
    4:0.16
    5:0.03
    6:0.02
    7:0.35
    8:0.03
    9:0.03
    10:0.08
    11:0.06
    Negative Logits
     dissenting
    -1.70
    iosyncr
    -1.56
    jah
    -1.52
    annon
    -1.50
    endiary
    -1.50
     proponent
    -1.49
    olute
    -1.48
    inately
    -1.48
    ente
    -1.48
    itte
    -1.47
    POSITIVE LOGITS
     unfold
    1.87
     vividly
    1.61
     scenes
    1.61
     Remem
    1.58
     likeness
    1.58
    Haunted
    1.57
     anew
    1.56
     nightmares
    1.54
     memories
    1.54
     basics
    1.54
    Act Density 0.002%

    No Known Activations