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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating age and significant life changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.08
    3:0.06
    4:0.03
    5:0.09
    6:0.13
    7:0.21
    8:0.08
    9:0.05
    10:0.14
    11:0.05
    Negative Logits
    Offline
    -1.32
     warranties
    -1.21
    HTTP
    -1.20
     airstrike
    -1.17
     clicks
    -1.16
     antiv
    -1.15
     aggregate
    -1.11
    blogs
    -1.10
     bount
    -1.09
     offline
    -1.08
    POSITIVE LOGITS
    enegger
    1.88
    cair
    1.54
    illard
    1.46
    kefeller
    1.44
    ��
    1.42
    uberty
    1.40
    ardless
    1.32
    enhagen
    1.32
    reditary
    1.30
    grave
    1.27
    Act Density 0.032%

    No Known Activations