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

    Neuronpedia

    INDEX
    Explanations

    phrases related to experiences and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibble
    -0.15
    uch
    -0.15
    avs
    -0.14
    aker
    -0.14
    setStatus
    -0.14
     Eth
    -0.14
    endas
    -0.14
    baz
    -0.14
    brane
    -0.13
    ä»®
    -0.13
    POSITIVE LOGITS
     easiest
    0.17
     best
    0.16
    atrice
    0.15
    788
    0.15
    thane
    0.15
     describing
    0.15
     description
    0.15
     ÄĮer
    0.14
    ære
    0.14
    urum
    0.14
    Act Density 0.159%

    No Known Activations