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

    Neuronpedia

    INDEX
    Explanations

    references to social dynamics and structures that affect power and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    instead
    -0.15
    inger
    -0.15
    awl
    -0.15
    raith
    -0.14
    Ỽt
    -0.14
    neau
    -0.14
     NAT
    -0.14
    jde
    -0.14
    aker
    -0.14
    ADATA
    -0.13
    POSITIVE LOGITS
     physical
    0.33
     overt
    0.32
     Physical
    0.30
    physical
    0.29
     obvious
    0.27
    Physical
    0.27
     explicit
    0.26
     direct
    0.26
     explicitly
    0.25
     visible
    0.24
    Act Density 0.333%

    No Known Activations