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

    Neuronpedia

    INDEX
    Explanations

    instances of psychological or health-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INCLUDED
    -0.18
     aforementioned
    -0.16
    eshire
    -0.13
    Âłin
    -0.12
     painstaking
    -0.12
     поба
    -0.12
    abyrin
    -0.12
    AAP
    -0.11
    ighth
    -0.11
    :↵
    -0.11
    POSITIVE LOGITS
    ,...↵↵
    0.14
    Ä°K
    0.13
     lesbi
    0.13
     âĶľ
    0.12
    ždy
    0.12
    kaç
    0.12
    Ä°S
    0.12
    oÄŁ
    0.12
    interopRequireDefault
    0.12
    λικ
    0.12
    Act Density 8.595%

    No Known Activations