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

    Neuronpedia

    INDEX
    Explanations

    technical terms or references related to computer science and technology

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to medical conditions and symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.57
     Adin
    -0.54
    Ö¼
    -0.52
    sylv
    -0.52
     Instr
    -0.50
    -+-+
    -0.49
    ttle
    -0.47
    enegger
    -0.46
    ^^^^
    -0.46
     exha
    -0.46
    POSITIVE LOGITS
     etc
    0.79
    !,
    0.61
     };
    0.60
     notwithstanding
    0.59
    ?,
    0.58
    )?
    0.58
     :=
    0.55
    00200000
    0.54
    ®,
    0.54
    !:
    0.53
    Act Density 0.704%

    No Known Activations