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

    Neuronpedia

    INDEX
    Explanations

    references to struggles with power dynamics and societal pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    532
    -0.17
    oze
    -0.17
    utting
    -0.16
     cracks
    -0.14
    MOTE
    -0.14
     handshake
    -0.14
    alette
    -0.14
    indr
    -0.14
     cling
    -0.13
     clinging
    -0.13
    POSITIVE LOGITS
     stuck
    0.42
     trapped
    0.38
     caught
    0.35
     forced
    0.31
    caught
    0.30
     faced
    0.28
    forced
    0.25
     sadd
    0.24
     thrust
    0.23
    locked
    0.23
    Act Density 0.530%

    No Known Activations