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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or multiple instances

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

    "In both cases" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    both cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.51
     utafitiHapana
    -0.42
    vignon
    -0.38
    ipheral
    -0.37
     rodríguez
    -0.37
    temon
    -0.36
     dul
    -0.36
    ContentAsync
    -0.34
    AndEndTag
    -0.34
    orde
    -0.34
    POSITIVE LOGITS
     Beide
    0.58
     begge
    0.56
     keduanya
    0.55
     ambos
    0.55
     båda
    0.54
    Both
    0.51
    jmniej
    0.50
     CWE
    0.49
    Kariera
    0.49
    Ambos
    0.49
    Act Density 0.494%

    No Known Activations