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

    Neuronpedia

    INDEX
    Explanations

    the presence of introductory phrases or markers signaling the start of a new section or thought within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.56
     &&
    -0.54
     based
    -0.53
     indisponible
    -0.51
    XPATH
    -0.49
     combined
    -0.49
     来自
    -0.48
     attention
    -0.48
    affili
    -0.47
     on
    -0.46
    POSITIVE LOGITS
    expandindo
    0.76
    mybatisplus
    0.70
     виправивши
    0.62
    Rüyada
    0.61
     estekak
    0.61
    AxisAlignment
    0.59
    Enllaces
    0.58
    Portale
    0.56
    Autoritní
    0.56
     méri
    0.56
    Act Density 0.053%

    No Known Activations