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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that express analysis or judgement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    caler
    -0.18
    oftware
    -0.16
    çĪ
    -0.15
     Brow
    -0.15
    rome
    -0.15
    chalk
    -0.14
    orne
    -0.14
    EEE
    -0.14
    ixer
    -0.14
    izin
    -0.14
    POSITIVE LOGITS
    rys
    0.15
    oden
    0.15
     Lace
    0.14
    ÙĴÙģ
    0.14
    /REC
    0.14
    .DropDown
    0.14
    illery
    0.14
    íĥĦ
    0.14
    çĽ
    0.14
    PRINTF
    0.14
    Act Density 0.001%

    No Known Activations