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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.77
    EDEFAULT
    -0.74
    rungsseite
    -0.71
     henvisninger
    -0.69
     AssemblyCulture
    -0.68
     jadx
    -0.67
    oredCriteria
    -0.66
     unknownFields
    -0.65
    jspb
    -0.64
     utafitiHapana
    -0.64
    POSITIVE LOGITS
    \
    1.16
    </strong>
    0.75
     &
    0.72
    <strong>
    0.66
    </em>
    0.64
    0.64
    ↵
    0.62
    </td>
    0.56
    </b>
    0.52
    $\
    0.51
    Act Density 0.032%
    No Known Activations