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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressions and their variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    août
    -0.60
    ůli
    -0.55
    North
    -0.53
    IfNot
    -0.52
     getItemId
    -0.51
     Autonomous
    -0.49
    aider
    -0.48
     Bakker
    -0.48
     NORTH
    -0.48
     Segurança
    -0.47
    POSITIVE LOGITS
     expression
    0.99
     expressions
    0.86
    expression
    0.83
     Expression
    0.83
     expre
    0.79
     express
    0.74
    Expression
    0.73
     Expressions
    0.73
     espressione
    0.72
     expresión
    0.71
    Act Density 0.047%

    No Known Activations