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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.17
    insk
    -0.16
    ãĥ©ãĥ¼
    -0.15
    ories
    -0.15
     Dump
    -0.15
    lej
    -0.14
    err
    -0.14
    ishly
    -0.14
     Moor
    -0.14
    ulta
    -0.13
    POSITIVE LOGITS
    pector
    0.15
    andy
    0.15
    ecko
    0.15
    emek
    0.14
    923
    0.14
    วย
    0.14
    canf
    0.14
    ANDLE
    0.14
    reator
    0.13
    _hd
    0.13
    Act Density 1.365%

    No Known Activations