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

    Neuronpedia

    INDEX
    Explanations

    phrases related to trust and reliability in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocket
    -0.19
    LOB
    -0.16
    ense
    -0.15
    leon
    -0.14
     amo
    -0.14
     per
    -0.14
    ¢åįķ
    -0.14
    ÌĨ
    -0.13
     دÙħ
    -0.13
    allet
    -0.13
    POSITIVE LOGITS
    wick
    0.16
    /by
    0.16
    ASURE
    0.15
    bett
    0.14
    ribly
    0.14
    udur
    0.14
    ĮĢ
    0.14
    äch
    0.14
     CrossRef
    0.14
    ì§Ŀ
    0.14
    Act Density 0.157%

    No Known Activations