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

    Neuronpedia

    INDEX
    Explanations

    concepts related to understanding and cognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ...↵
    -0.32
    ...)↵
    -0.28
    ,...↵
    -0.27
    ...'↵
    -0.25
    ....↵
    -0.24
    .*/↵
    -0.24
    ;↵
    -0.24
    */↵
    -0.23
    ↵
    -0.23
    >↵
    -0.23
    POSITIVE LOGITS
     âĢ¦
    0.65
    â
    0.50
     [âĢ¦]
    0.48
     â
    0.48
     [âĢ¦
    0.36
    âĢ¦
    0.33
    .eval
    0.32
    .".
    0.31
     ...
    0.31
    ..
    0.30
    Act Density 0.174%

    No Known Activations