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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attention and guidance in a professional or customer-focused context

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

    choose wisely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeText
    -0.58
    StructEnd
    -0.52
    Tikang
    -0.51
    Ҭ
    -0.50
    ScopeManager
    -0.49
    <?
    -0.48
    قایناق‌لار
    -0.47
    bootstrapcdn
    -0.46
    tifact
    -0.46
    BASEPATH
    -0.46
    POSITIVE LOGITS
     yourself
    0.73
     your
    0.64
     yourselves
    0.63
    your
    0.57
    yourself
    0.55
     Yourself
    0.53
     YOURSELF
    0.52
     YOUR
    0.46
     ваших
    0.46
     Take
    0.45
    Act Density 1.703%

    No Known Activations