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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recommendations or endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     du
    -0.16
     enc
    -0.15
    ses
    -0.15
    .vn
    -0.15
    459
    -0.15
    uria
    -0.15
    #w
    -0.15
    462
    -0.14
    ebra
    -0.14
    713
    -0.13
    POSITIVE LOGITS
    age
    0.21
    bes
    0.17
    ¶ģ
    0.17
    obao
    0.16
    ãģ¤ãģ¶
    0.15
    ugin
    0.15
    ãĤŃãĥ¥
    0.15
    wards
    0.15
    ugins
    0.15
    'gc
    0.15
    Act Density 0.066%

    No Known Activations