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

    Neuronpedia

    INDEX
    Explanations

    references to individuals in narrative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.08
    2:0.11
    3:0.10
    4:0.05
    5:0.06
    6:0.11
    7:0.07
    8:0.12
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
     hindsight
    -1.00
    Wan
    -0.97
     actionGroup
    -0.94
     Thrones
    -0.91
    Plex
    -0.89
    ��
    -0.88
    CLASSIFIED
    -0.88
     Subtle
    -0.86
     wasteland
    -0.86
     TTL
    -0.85
    POSITIVE LOGITS
    igl
    1.23
    said
    1.08
    aryl
    1.02
    aughed
    0.99
    iannopoulos
    0.97
    neau
    0.96
    jc
    0.96
    onga
    0.95
     Said
    0.94
    affer
    0.94
    Act Density 0.025%

    No Known Activations