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

    Neuronpedia

    INDEX
    Explanations

    references to lists and examples that describe change or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    мин
    -0.15
    ¹Ħ
    -0.14
    å°ĺ
    -0.14
    мÑĸн
    -0.14
    jes
    -0.14
    incer
    -0.14
     Vand
    -0.14
     paid
    -0.13
    .house
    -0.13
    ARGET
    -0.13
    POSITIVE LOGITS
    nych
    0.16
    ÏĥÏħ
    0.15
    nock
    0.14
    ì½
    0.14
    soever
    0.14
    ña
    0.14
    ITHER
    0.14
    hower
    0.14
    PRI
    0.14
     æĤ
    0.14
    Act Density 0.121%

    No Known Activations