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

    Neuronpedia

    INDEX
    Explanations

    references to statistical measures or parameters related to testing and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Campion
    -0.77
     vå
    -0.72
     Benav
    -0.72
     Bassi
    -0.70
     Browne
    -0.70
    Benson
    -0.70
    ]**
    -0.69
    butik
    -0.69
     Benson
    -0.68
     desmon
    -0.67
    POSITIVE LOGITS
    r
    1.56
    er
    1.28
    R
    1.23
    rrr
    1.22
    rrrrr
    1.17
    tr
    1.15
    pr
    1.09
     r
    1.07
    rrrr
    1.05
    vr
    1.05
    Act Density 0.379%

    No Known Activations