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

    Neuronpedia

    INDEX
    Explanations

    terms related to superiority or improved status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oba
    -0.18
    Enums
    -0.16
    chine
    -0.16
    gap
    -0.15
    835
    -0.14
     dobÅĻe
    -0.14
    -gap
    -0.14
    ulas
    -0.14
    kup
    -0.14
    liner
    -0.13
    POSITIVE LOGITS
    -su
    0.23
     prepared
    0.23
    su
    0.22
     suited
    0.22
     served
    0.21
    -position
    0.21
    Su
    0.21
     Su
    0.20
    prepared
    0.20
     situated
    0.20
    Act Density 0.043%

    No Known Activations