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

    Neuronpedia

    INDEX
    Explanations

    the repetitive use of the word "ever" in various contexts

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

    occurrence or non-occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.54
    bootstrapcdn
    -0.52
    complexType
    -0.51
    <?=$
    -0.50
     organiza
    -0.49
     AOC
    -0.49
     Initialized
    -0.48
     endblock
    -0.48
    HashCode
    -0.47
     Mime
    -0.46
    POSITIVE LOGITS
     ever
    1.69
     EVER
    1.52
    ever
    1.48
    Ever
    1.45
     Ever
    1.41
    EVER
    1.19
     jemals
    1.16
     jamás
    1.10
     pernah
    1.02
    never
    1.00
    Act Density 0.007%

    No Known Activations