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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "purely"

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

    purely followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Obrador
    -0.48
    ſelf
    -0.46
     ſon
    -0.46
    VPB
    -0.46
    Nid
    -0.44
     houſe
    -0.44
     Annotated
    -0.43
    館
    -0.43
    ことがあります
    -0.43
    MMS
    -0.42
    POSITIVE LOGITS
     purely
    1.73
     puramente
    1.22
     strictly
    0.87
    纯粹
    0.84
     чисто
    0.82
    pure
    0.81
     Pure
    0.74
     PURE
    0.71
     merely
    0.70
    Pure
    0.70
    Act Density 0.008%

    No Known Activations