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

    Neuronpedia

    INDEX
    Explanations

    phrases related to chat systems and their development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    656
    -0.15
     éĬ
    -0.15
     epith
    -0.15
     xhttp
    -0.15
    éĶĢ
    -0.15
     Mattis
    -0.14
    оÑĢоÑĤ
    -0.14
    acin
    -0.14
    _INCLUDED
    -0.14
     exhaustion
    -0.13
    POSITIVE LOGITS
    prompt
    0.25
     prompt
    0.23
    BERT
    0.23
     Prompt
    0.23
    bert
    0.23
     prompts
    0.22
     bert
    0.21
    .prompt
    0.21
    Prompt
    0.21
    _prompt
    0.21
    Act Density 0.010%

    No Known Activations