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

    Neuronpedia

    INDEX
    Explanations

    terms related to analysis and assessment methodologies

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ness
    -1.05
    er
    -0.98
    nya
    -0.88
    m
    -0.82
    nt
    -0.73
    r
    -0.71
    ner
    -0.71
    n
    -0.70
    ms
    -0.66
    mon
    -0.65
    POSITIVE LOGITS
     Theſe
    1.05
    ative
    1.05
     Houſe
    1.00
     myſelf
    0.99
     ſeveral
    0.97
    Kariera
    0.93
     themſelves
    0.93
    batore
    0.91
     ſmall
    0.89
     Diſ
    0.87
    Act Density 0.113%

    No Known Activations