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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or usefulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ldb
    -0.14
    mor
    -0.14
     ram
    -0.14
    \grid
    -0.14
     Felix
    -0.14
     rash
    -0.13
    rips
    -0.13
    Weights
    -0.13
    onomy
    -0.13
    mun
    -0.13
    POSITIVE LOGITS
     purposes
    0.20
    yna
    0.18
    ÏĦÏģο
    0.16
    dust
    0.15
    κοÏĤ
    0.15
     reasons
    0.15
    amina
    0.15
    usement
    0.15
    upe
    0.15
    ays
    0.14
    Act Density 0.352%

    No Known Activations