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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating locations or sites related to significant events or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.03
    4:0.10
    5:0.02
    6:0.08
    7:0.40
    8:0.02
    9:0.02
    10:0.13
    11:0.06
    Negative Logits
     uncond
    -1.86
     actionGroup
    -1.59
    osponsors
    -1.58
    ixie
    -1.58
    ahs
    -1.54
     guiIcon
    -1.52
    icient
    -1.47
     louder
    -1.47
    orters
    -1.45
    iren
    -1.44
    POSITIVE LOGITS
    site
    1.78
     site
    1.64
     archives
    1.56
    bsite
    1.50
     redevelopment
    1.48
    castle
    1.46
     temple
    1.44
     Titanic
    1.42
     downtown
    1.42
     historic
    1.40
    Act Density 0.009%

    No Known Activations