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

    Neuronpedia

    INDEX
    Explanations

    concerns about problems or issues in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RITE
    -0.17
    ERP
    -0.15
    ardon
    -0.15
     BOTH
    -0.15
    ighter
    -0.14
    awah
    -0.14
    imit
    -0.14
    çĽ
    -0.14
    both
    -0.14
    IMITIVE
    -0.14
    POSITIVE LOGITS
     nor
    0.31
     anymore
    0.27
     except
    0.27
    nor
    0.26
    except
    0.23
    à¹ĥà¸Ķ
    0.19
    Except
    0.19
    Nor
    0.19
     Except
    0.18
     really
    0.18
    Act Density 0.201%

    No Known Activations