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

    Neuronpedia

    INDEX
    Explanations

    qualitative descriptors related to performance and competitiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enough
    -0.19
    ink
    -0.16
     Enough
    -0.15
    eln
    -0.15
    ffen
    -0.14
    assen
    -0.14
    åºŃ
    -0.14
    ients
    -0.14
     sufficient
    -0.14
    asse
    -0.14
    POSITIVE LOGITS
     than
    0.35
    -than
    0.30
    _than
    0.28
    than
    0.26
     THAN
    0.26
     Than
    0.26
    Than
    0.25
     niż
    0.23
    _THAN
    0.18
     než
    0.18
    Act Density 0.270%

    No Known Activations