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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "by" and its variations

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

    identifying methods or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.67
    AddTagHelper
    -0.63
    CppMethod
    -0.59
    olerance
    -0.57
    ſehen
    -0.56
    ApiModelProperty
    -0.55
    =$?
    -0.54
    EDEFAULT
    -0.52
    lanatory
    -0.52
    nash
    -0.52
    POSITIVE LOGITS
    By
    0.61
     By
    0.60
    ammans
    0.43
    することで
    0.43
     Dzięki
    0.36
    Through
    0.34
    Using
    0.34
     consigue
    0.34
    With
    0.34
    GraphicsUnit
    0.33
    Act Density 0.021%

    No Known Activations