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

    Neuronpedia

    INDEX
    Explanations

    references to authorship and attribution in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rys
    -0.15
    IQ
    -0.14
    eks
    -0.14
    elman
    -0.14
     Rhodes
    -0.14
     wholesale
    -0.13
    \brief
    -0.13
    achine
    -0.13
    nesty
    -0.13
    elf
    -0.13
    POSITIVE LOGITS
    _tokenize
    0.15
    fillType
    0.15
    ilir
    0.15
    ENTA
    0.14
    INCT
    0.14
    £i
    0.14
    ilt
    0.13
    cky
    0.13
    .quant
    0.13
    ildenafil
    0.13
    Act Density 0.010%

    No Known Activations