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

    Neuronpedia

    INDEX
    Explanations

    the word "even" in various contexts

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

    "Even" followed by a contrasting word/phrase

    np_acts-logits-general · gemini-2.0-flash

    even though / even if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Either
    -0.92
    Parcelize
    -0.90
     Either
    -0.89
    TagMode
    -0.85
    either
    -0.85
    UnusedPrivate
    -0.82
     BoxFit
    -0.80
     entweder
    -0.79
    AutoresizingMask
    -0.77
    also
    -0.76
    POSITIVE LOGITS
     though
    1.29
    though
    1.08
     THOUGH
    1.00
    Though
    0.86
     Though
    0.84
     worse
    0.83
    handed
    0.81
     remotely
    0.72
     tho
    0.72
    handedly
    0.72
    Act Density 0.098%

    No Known Activations