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

    Neuronpedia

    INDEX
    Explanations

    objects represented by empty objects or dictionaries in data structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <i>
    -0.66
    <blockquote>
    -0.65
    <b>
    -0.62
    end
    -0.59
    ina
    -0.59
    we
    -0.59
    </td>
    -0.58
    ere
    -0.57
    </i>
    -0.56
    in
    -0.56
    POSITIVE LOGITS
    FormTagHelper
    0.93
     Holman
    0.88
    ProcessEvent
    0.82
     AppCompat
    0.82
    olesale
    0.81
    endroit
    0.81
    idać
    0.81
     pinulongan
    0.81
    arranty
    0.81
     himſelf
    0.81
    Act Density 0.015%

    No Known Activations