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

    Neuronpedia

    INDEX
    Explanations

    themes related to societal criticism and existential concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irt
    -0.15
     ped
    -0.15
     magic
    -0.14
     Sed
    -0.14
     Harmon
    -0.14
    imer
    -0.13
     Pink
    -0.13
     Kant
    -0.13
    obl
    -0.13
     Echo
    -0.13
    POSITIVE LOGITS
    orda
    0.17
    ouro
    0.17
    PERT
    0.15
    uess
    0.15
    ULL
    0.15
    ihan
    0.14
     nonlinear
    0.14
    .scalablytyped
    0.14
    çĶ
    0.14
    onna
    0.14
    Act Density 0.308%

    No Known Activations