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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize superiority or exceptional qualities

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

    be the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.55
    arkhand
    -0.53
    хьтан
    -0.53
     arşivlendi
    -0.50
    lankton
    -0.50
    ckles
    -0.48
    endaten
    -0.48
    oter
    -0.48
    rostis
    -0.48
    outlined
    -0.48
    POSITIVE LOGITS
    Become
    0.47
     Become
    0.46
     become
    0.42
     Menjadi
    0.42
    become
    0.41
    Be
    0.41
     becomes
    0.38
    neté
    0.37
     Be
    0.37
     Becomes
    0.37
    Act Density 0.023%

    No Known Activations