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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating honesty or sincerity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aver
    -0.16
    âĢı
    -0.15
    ç¯Ģ
    -0.15
    na
    -0.15
    arin
    -0.14
    gesch
    -0.14
    Ñģ
    -0.14
    gas
    -0.14
     ultimate
    -0.14
    rous
    -0.14
    POSITIVE LOGITS
    ewis
    0.19
    iyel
    0.18
    upp
    0.17
    -Sah
    0.16
    æ£ļ
    0.15
    enance
    0.15
    heits
    0.15
    ifax
    0.15
    LTR
    0.14
    anchors
    0.14
    Act Density 0.024%

    No Known Activations