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

    Neuronpedia

    INDEX
    Explanations

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     giapp
    -0.64
     tecnici
    -0.63
     Shaffer
    -0.62
     soldati
    -0.61
     amanda
    -0.58
     japonais
    -0.57
     bună
    -0.56
     liitty
    -0.56
     noastră
    -0.54
     jepang
    -0.53
    POSITIVE LOGITS
    abestanden
    0.90
    LayoutStyle
    0.72
    scriptcase
    0.69
    cplusplus
    0.69
    Gizmos
    0.69
     فريبيس
    0.68
    ranean
    0.67
    DebuggerNonUser
    0.67
    */;
    0.67
    {{/
    0.64
    Act Density 0.001%

    No Known Activations