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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or intentions

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

    "To" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    to have or to see

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Activité
    -0.64
    Vorte
    -0.61
    scriptcase
    -0.61
    łku
    -0.61
    zarchiwizowane
    -0.60
    èrement
    -0.58
    gonic
    -0.58
    исленность
    -0.58
    ynb
    -0.57
    istration
    -0.56
    POSITIVE LOGITS
     me
    0.80
     suddenly
    0.66
     having
    0.63
     indeed
    0.57
     Having
    0.57
    Having
    0.55
     want
    0.55
     rius
    0.55
     suppose
    0.53
    Jegyzetek
    0.53
    Act Density 0.202%

    No Known Activations