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

    Neuronpedia

    INDEX
    Explanations

    topics related to social or economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.21
    1:0.03
    2:0.10
    3:0.03
    4:0.10
    5:0.07
    6:0.04
    7:0.05
    8:0.20
    9:0.03
    10:0.04
    11:0.07
    Negative Logits
    hesis
    -1.41
    686
    -1.33
    acion
    -1.31
    ":["
    -1.31
     Malays
    -1.27
     Liberation
    -1.25
    arten
    -1.25
     Nobel
    -1.25
    Assembly
    -1.24
     Bian
    -1.22
    POSITIVE LOGITS
     whichever
    1.71
     UCHIJ
    1.57
     overrun
    1.44
     defy
    1.37
    into
    1.36
    arin
    1.35
     Unloaded
    1.34
    oward
    1.33
    cens
    1.31
     Suddenly
    1.31
    Act Density 0.022%

    No Known Activations