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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "even" in various forms and contexts

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

    "Even" followed by a conditional word

    np_acts-logits-general · gemini-2.0-flash

    even followed by contrasting conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.84
    UnusedPrivate
    -0.75
    JsonPropertyName
    -0.74
    JvmStatic
    -0.73
    offsetof
    -0.70
     Rigidbody
    -0.68
    Koordin
    -0.66
    createCanvas
    -0.65
    also
    -0.65
    bufio
    -0.65
    POSITIVE LOGITS
     though
    0.95
     remotely
    0.80
    though
    0.77
     EVEN
    0.77
    handed
    0.77
     even
    0.76
    ement
    0.73
     THOUGH
    0.73
    Though
    0.69
    Slight
    0.69
    Act Density 0.081%

    No Known Activations