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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to conversational AI and chat systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upo
    -0.12
    plr
    -0.11
    że
    -0.11
     xa
    -0.11
    ź
    -0.11
    outil
    -0.11
    erç
    -0.11
    Ìģt
    -0.10
    .mongodb
    -0.10
    usercontent
    -0.10
    POSITIVE LOGITS
     [âĢ¦
    0.16
     âĢ¦↵
    0.15
     [âĢ¦]
    0.15
    âĢ¦âĢ¦âĢ¦âĢ¦
    0.14
     ÂŃ
    0.14
     “âĢ¦
    0.14
     âĢ¦
    0.14
     [âĢ¦]↵
    0.14
    âĢ¦
    0.14
     âĢ¦.
    0.14
    Act Density 8.995%

    No Known Activations