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

    Neuronpedia

    INDEX
    Explanations

    themes related to political critique and societal constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ledged
    -0.15
    haul
    -0.14
     Loaded
    -0.14
    elligent
    -0.14
    OPS
    -0.13
    uu
    -0.13
    yles
    -0.13
    235
    -0.13
    åıĬ
    -0.13
     fick
    -0.13
    POSITIVE LOGITS
     mas
    0.23
    mas
    0.20
     meant
    0.19
    Mas
    0.18
     Mas
    0.18
     unlikely
    0.18
     dreamed
    0.17
     designed
    0.17
     dream
    0.16
     whose
    0.16
    Act Density 0.236%

    No Known Activations