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

    Neuronpedia

    INDEX
    Explanations

    instances of string literals, particularly with specific quote and delimiter characters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.89
    djangoproject
    -0.75
    SequentialGroup
    -0.75
    RepeatedField
    -0.67
     po
    -0.67
     AssemblyCulture
    -0.66
    nocache
    -0.62
    ↵
    -0.60
    [toxicity=0]
    -0.60
    EndContext
    -0.58
    POSITIVE LOGITS
     pleaſure
    1.25
     raiſ
    1.20
     juſt
    1.12
    !("{
    1.08
     purpoſe
    1.08
     faſt
    1.07
     ſen
    1.07
     Anſ
    1.05
     Inſ
    1.02
     myſelf
    1.02
    Act Density 0.124%

    No Known Activations