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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "first" and its variants in various contexts

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

    before or first

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.50
    principalColumn
    -0.49
    fjspx
    -0.48
    SafeMath
    -0.45
    fej
    -0.43
    MigrationBuilder
    -0.42
    hyrchwyd
    -0.42
     Jodie
    -0.41
    Microkernel
    -0.40
    躾
    -0.40
    POSITIVE LOGITS
     préalable
    0.50
     InputDecoration
    0.46
     auparavant
    0.45
     предвари
    0.43
     previamente
    0.41
    tagext
    0.40
    paravant
    0.40
     vorher
    0.39
     zuvor
    0.39
     Before
    0.38
    Act Density 0.190%

    No Known Activations