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

    Neuronpedia

    INDEX
    Explanations

    the preposition "to" in various contexts

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

    remember to + verb instruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inconnu
    -0.53
     newData
    -0.51
     virtuel
    -0.48
     ressemb
    -0.47
     Мексичка
    -0.47
    WriteLiteral
    -0.45
     chien
    -0.45
     vœ
    -0.44
     connaissance
    -0.44
     jednost
    -0.44
    POSITIVE LOGITS
     always
    0.62
     обязательно
    0.59
     remember
    0.54
    Always
    0.54
    always
    0.54
     include
    0.53
    remember
    0.52
    必ず
    0.50
     برانيه
    0.50
     mention
    0.50
    Act Density 0.004%

    No Known Activations