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

    Neuronpedia

    INDEX
    Explanations

    phrases related to transparency in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ataire
    -0.15
    iyan
    -0.15
    indsight
    -0.14
    ujet
    -0.13
    çĦ¡ãģĹ
    -0.13
    orias
    -0.13
    aliz
    -0.13
     Favor
    -0.13
    å¾Ħ
    -0.13
     iddi
    -0.13
    POSITIVE LOGITS
    101
    0.21
    360
    0.20
    200
    0.16
    ï¸ı
    0.16
    001
    0.16
    201
    0.16
    oub
    0.16
    enson
    0.15
    mk
    0.15
    klady
    0.15
    Act Density 0.155%

    No Known Activations