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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts

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

    but not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.50
    HasIndex
    -0.50
     vandens
    -0.49
     ffilm
    -0.47
    Билгалдахарш
    -0.47
     Tasche
    -0.46
    ">//
    -0.45
    HasAnnotation
    -0.45
    stylers
    -0.45
    Бахар
    -0.44
    POSITIVE LOGITS
    Alpes
    0.37
    พาะ
    0.37
     Nat
    0.36
    但不
    0.36
     MainAxisSize
    0.36
     незавершена
    0.35
     Gob
    0.35
     Ci
    0.35
     gu
    0.35
     Lit
    0.35
    Act Density 0.039%

    No Known Activations