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

    Neuronpedia

    INDEX
    Explanations

    phrases related to lasting impacts and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aniel
    -0.17
    oun
    -0.15
    lex
    -0.14
    ²
    -0.14
     firm
    -0.14
    eman
    -0.14
    lov
    -0.14
    lok
    -0.14
    leta
    -0.14
    PIX
    -0.14
    POSITIVE LOGITS
    casting
    0.15
    кав
    0.15
     forever
    0.14
    /Open
    0.14
    ãĥ³ãĥIJ
    0.14
     Vers
    0.14
    occan
    0.14
    arus
    0.14
    ÙĬÙĨÙĬ
    0.14
    rug
    0.13
    Act Density 0.082%

    No Known Activations