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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" and its variations, reflecting a focus on comparatives and inclusivity in statements

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

    similarity or addition

    np_acts-logits-general · gemini-2.0-flash

    also, too, similarly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.47
    ///</
    -0.46
    HideFlags
    -0.41
    httphttps
    -0.40
    AutoField
    -0.40
    thalt
    -0.36
     Jenderal
    -0.36
    >{@
    -0.34
     Leve
    -0.34
    typeorm
    -0.34
    POSITIVE LOGITS
     וגם
    0.61
    кож
    0.60
    ckså
    0.60
     TAMBIÉN
    0.58
    něž
    0.58
     similarly
    0.55
     TAMBÉM
    0.53
     turut
    0.51
    gså
    0.50
    こちらも
    0.50
    Act Density 0.384%

    No Known Activations