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

    Neuronpedia

    INDEX
    Explanations

    intensity and exaggeration in descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ​
    -0.30
     compañías
    -0.28
     estratégico
    -0.26
     poussière
    -0.26
     supérieur
    -0.25
     Económica
    -0.25
     officers
    -0.24
    ằm
    -0.24
    potensi
    -0.24
     relógio
    -0.23
    POSITIVE LOGITS
     kasarigan
    0.93
    AndEndTag
    0.85
    writeFieldEnd
    0.81
    Autoritní
    0.81
     パンチラ
    0.79
    <unused47>
    0.77
    <unused74>
    0.77
    <unused41>
    0.77
    <unused3>
    0.77
    <unused28>
    0.77
    Act Density 0.031%

    No Known Activations