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

    Neuronpedia

    INDEX
    Explanations

    concepts related to grounding and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otland
    -0.17
    orda
    -0.15
    wich
    -0.15
    .gnu
    -0.14
    latin
    -0.14
     Trace
    -0.14
    vertime
    -0.14
    erken
    -0.14
     strict
    -0.14
     Strict
    -0.14
    POSITIVE LOGITS
     Sad
    0.23
    Sad
    0.19
     sad
    0.17
     Ling
    0.17
    CSR
    0.16
     inclus
    0.15
    clusive
    0.15
     vive
    0.15
     Inner
    0.14
    ocre
    0.14
    Act Density 0.001%

    No Known Activations