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

    Neuronpedia

    INDEX
    Explanations

    words related to investigations or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the character "ľ."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.69
    rawdownloadcloneembedreportprint
    -0.69
     similarities
    -0.66
    orial
    -0.65
     primates
    -0.65
     AAC
    -0.64
     gist
    -0.64
    matic
    -0.63
     similarity
    -0.63
     terminals
    -0.63
    POSITIVE LOGITS
    ľ
    1.13
    âĶĢâĶĢ
    1.06
    ¸
    0.92
    âĶĢâĶĢâĶĢâĶĢ
    0.92
    ĸ
    0.92
    Ĺ
    0.91
    ª
    0.91
    ¼
    0.91
    ļ
    0.88
    à©
    0.86
    Act Density 0.266%

    No Known Activations