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

    Neuronpedia

    INDEX
    Explanations

    negative assertions or phrases indicating something is not functioning or available

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     meiden
    -0.15
     Only
    -0.14
    ropri
    -0.14
     saja
    -0.14
     somew
    -0.14
     slightly
    -0.13
     apenas
    -0.13
     Humph
    -0.13
     ONLY
    -0.13
     Som
    -0.13
    POSITIVE LOGITS
     supported
    0.26
     yet
    0.22
    -supported
    0.22
    supported
    0.22
    found
    0.19
    yet
    0.19
     found
    0.19
     support
    0.18
     recon
    0.18
     Supported
    0.18
    Act Density 0.155%

    No Known Activations