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

    Neuronpedia

    INDEX
    Explanations

    statements that assert the existence of certain facts or truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peria
    -0.17
    foundland
    -0.15
    baugh
    -0.15
    NODE
    -0.15
    ederland
    -0.14
    å·®
    -0.14
     trÆ°á»Łng
    -0.14
    swer
    -0.14
     Erf
    -0.14
    еко
    -0.14
    POSITIVE LOGITS
    ease
    0.16
    ea
    0.15
    BLUE
    0.15
    lan
    0.15
    824
    0.14
    Ease
    0.14
    haar
    0.14
     Blue
    0.14
    stantiate
    0.14
    oth
    0.14
    Act Density 0.015%

    No Known Activations