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

    Neuronpedia

    INDEX
    Explanations

    information related to research studies and their findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afx
    -0.16
    _simps
    -0.15
    resher
    -0.15
    ersonic
    -0.14
    поÑĢ
    -0.14
     Pig
    -0.14
    pon
    -0.14
    pig
    -0.14
     defer
    -0.13
    ritz
    -0.13
    POSITIVE LOGITS
    /report
    0.18
     diarr
    0.18
     diary
    0.18
     Lifestyle
    0.17
     khai
    0.16
     å¿
    0.15
    kh
    0.15
     diarrhea
    0.15
     Self
    0.15
    yne
    0.15
    Act Density 0.083%

    No Known Activations