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

    Neuronpedia

    INDEX
    Explanations

    references to the final version of a manuscript

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.78
     الحره
    -0.77
     pinulongan
    -0.70
    مصادر
    -0.64
     nakalista
    -0.63
     autorytatywna
    -0.61
    rungsseite
    -0.60
    مراجع
    -0.58
    曖昧さ回避
    -0.56
    енча
    -0.54
    POSITIVE LOGITS
    mybatisplus
    0.52
    Mention
    0.50
     ſhe
    0.50
     ſtre
    0.50
     blowout
    0.50
     defaultstate
    0.49
     ſta
    0.49
     Bastard
    0.48
    SequentialGroup
    0.47
    MENAFN
    0.47
    Act Density 0.002%

    No Known Activations