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

    Neuronpedia

    INDEX
    Explanations

    references to the recipient or audience in communication

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

    you that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proprement
    -0.51
     LIRE
    -0.47
    someone
    -0.45
    mybatisplus
    -0.44
     houſe
    -0.43
     amitié
    -0.43
    sleepy
    -0.41
    inSlope
    -0.41
     smelling
    -0.41
     salaire
    -0.41
    POSITIVE LOGITS
    ंदीखरीदारी
    0.51
    WriteTagHelper
    0.45
    matchCondition
    0.44
    enterOuterAlt
    0.44
     مشين
    0.44
    setopt
    0.43
    AddTagHelper
    0.41
    ImageContext
    0.39
     Sacrament
    0.38
    تقاوى
    0.38
    Act Density 0.022%

    No Known Activations